philbert440/Qwen3.6-27B-Uncensored-Cyber
Abliterated vs Qwen/Qwen3.6-27B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 54 of 64 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/5, MLP 39/307, Attention 54/560, lm_head 0/1, Norms 0/325, other 0/1
1 derivatives checked
- mradermacher/Qwen3.6-27B-Uncensored-Cyber-GGUF: Quantization