meangrinch/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distill-heretic-v3

Abliterated vs meangrinch/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distill. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 9 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.

Tensors changed: Embeddings 0/4, MLP 8/196, Attention 9/320, Norms 0/203

3 derivatives checked

On the Hub · Downloads on Model Pulse