{ "architecture": "DFC", "model_a": "chengq9/ToolRL-Qwen2.5-3B", "model_b": "Qwen/Qwen2.5-3B", "layer": 13, "activation_dim": 2048, "dict_size": 8192, "k": 90, "model_a_exclusive_pct": 0.10, "model_b_exclusive_pct": 0.10, "steps": 9000, "lr": 1e-4, "train_batch": 1024, "sparsity_coef": 1e-3, "exclusive_sparsity_coef": 0, "loss": "MSE + L1 on shared features only (coef: 1e-3); exclusive features unpenalized", "wandb_project": "dfc-crosscoder-sweep", "trained_at": "2026-03-30T05:03:28+00:00" }