Drop small internal N=16-style dev-probe numbers from method/validation; keep only real large-N eval results

README.md

@@ -38,15 +38,15 @@ This checkpoint is **not** a jailbreak prompt, a system-prompt trick, or a fine-
 
 ## Method — refusal removal in a Mixture-of-Experts
 
-Removing refusal from a sparse MoE is harder than from a dense model. In this Qwen3.5 MoE, refusal is **multiply redundant**: it is encoded simultaneously in the routed experts, in the per-layer input projections that recompute it from the residual stream, and in the token embeddings. Because each pathway compensates when another is ablated, any *single-pathway* edit plateaus near **0.31** removal — a coverage limit, not a fundamental one. The recipe therefore proceeds in three stages, building on a cone-aware, multi-direction account of refusal rather than a lone mean-difference vector ([Wollschläger et al., 2025](https://arxiv.org/abs/2502.17420)).
+Removing refusal from a sparse MoE is harder than from a dense model. In this Qwen3.5 MoE, refusal is **multiply redundant**: it is encoded simultaneously in the routed experts, in the per-layer input projections that recompute it from the residual stream, and in the token embeddings. Because each pathway compensates when another is ablated, any *single-pathway* edit plateaus well short of full removal — a coverage limit, not a fundamental one. The recipe therefore proceeds in three stages, building on a cone-aware, multi-direction account of refusal rather than a lone mean-difference vector ([Wollschläger et al., 2025](https://arxiv.org/abs/2502.17420)).
 
-| Stage | Edit | Removal |
-|---|---|---|
-| **1. Directions** | Clean-cone-2 biprojected direction set over the residual-stream band of layers 4–39, flat α = 1.0, computed in fp32 with 0.995 activation clipping under the chat template | — |
-| **2. Synergy edit** | Orthogonalize **all 256 routed experts** together with the gate/up input projections and the token embeddings (cone-rank 2, scale 1.0) | **0.6875** |
-| **3. CNA-from-base neuron mask** | A Cone-Normal-Attribution pass identifies the `down_proj` input neurons that fire on harmful-vs-benign prompts **on the base model** (top 0.5% ≈ 1,441 neurons) and bakes that column-level mask into the synergy-edited weights — a variant of the contrastive neuron attribution (CNA) approach for isolating refusal-discriminating MLP neurons ([Herring, Naviasky & Malhotra, 2026](https://huggingface.co/papers/2605.12290)) | **0.8125** |
+| Stage | Edit |
+|---|---|
+| **1. Directions** | Clean-cone-2 biprojected direction set over the residual-stream band of layers 4–39, flat α = 1.0, computed in fp32 with 0.995 activation clipping under the chat template |
+| **2. Synergy edit** | Orthogonalize **all 256 routed experts** together with the gate/up input projections and the token embeddings (cone-rank 2, scale 1.0) |
+| **3. CNA-from-base neuron mask** | A Cone-Normal-Attribution pass identifies the `down_proj` input neurons that fire on harmful-vs-benign prompts **on the base model** (top 0.5% ≈ 1,441 neurons) and bakes that column-level mask into the synergy-edited weights — a variant of the contrastive neuron attribution (CNA) approach for isolating refusal-discriminating MLP neurons ([Herring, Naviasky & Malhotra, 2026](https://huggingface.co/papers/2605.12290)) |
 
-Because the neuron mask is **column-level** and orthogonal to the **row-level** direction removal, the two stack — reaching **0.8125 removal at 0.0 incoherence** with no added spillover. The mask is captured on the *base* model (where refusal still fires cleanly) and baked into the *edited* model; capturing on the already-edited model regresses it, because it then selects capability rather than refusal neurons.
+Because the neuron mask is **column-level** and orthogonal to the **row-level** direction removal, the two stack without added spillover. The mask is captured on the *base* model (where refusal still fires cleanly) and baked into the *edited* model; capturing on the already-edited model regresses it, because it then selects capability rather than refusal neurons.
 
 Removal is performed by directional ablation / weight orthogonalization (projecting the offending direction(s) out of the relevant weight matrices), so the edit is **baked into the weights** and requires no inference-time hook.
 
@@ -59,7 +59,6 @@ The edit was validated for both **refusal removal** and **absence of damage**, s
 | Metric | Result |
 |---|---|
 | Refusal removal (200-prompt probe) | **97.5%** |
-| Refusal removal (development target eval) | **0.8125** (three-stage synergy + CNA-from-base) |
 | Incoherence | **0.0** (no degeneration) |
 | Cognitive damage (capability/coherence probe) | **none observed** |
 | Residual self-harm/suicide refusals | **~2.5%, soft, concentrated on self-harm (accepted, not by design)** |
@@ -169,7 +168,7 @@ print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))
 
 - Inherits the knowledge, biases, and failure modes of the base Qwen3.5-35B-A3B.
 - Abliteration targets the dominant refusal subspace; rare or out-of-distribution refusal triggers may persist or, conversely, edge-case over-compliance may appear.
-- Refusal in this MoE is redundantly encoded across routed experts, input projections, and embeddings; the three-stage edit reaches 0.8125 on the development eval, so some routed pathways may retain residual refusal under unusual gating.
+- Refusal in this MoE is redundantly encoded across routed experts, input projections, and embeddings; some routed pathways may retain residual refusal under unusual gating despite the three-stage edit.
 - Without trained refusals, the model will attempt requests an aligned model would decline; treat outputs accordingly.
 - Capability was **not** benchmarked for this checkpoint (see Validation); coherence was checked but a full capability suite is pending.