saidutta69/Qwen3-VL-8B-Instruct-heretic
Abliterated vs Qwen/Qwen3-VL-8B-Instruct. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 31 of 36 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/4, Norms 0/261, MLP 31/232, Attention 29/252, lm_head 0/1