YunoAIdotcom/Qwen3-14B-RefusalDirection-ThinkingAware
Abliterated vs Qwen/Qwen3-14B. Looks like abliteration (refusal removal): only the output projections (down_proj, embed_tokens, o_proj) changed, in 40 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 1/1, Norms 0/161, MLP 40/120, Attention 40/160, lm_head 0/1