temaq-org/Tema_Q-X3-Thinking
Abliterated vs Qwen/Qwen3.5-35B-A3B. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj, out_proj) changed, in 40 of 40 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: MLP 337/1165, lm_head 0/1, Embeddings 0/5, Attention 41/392, other 0/1, Norms 0/247
1 derivatives checked
- mradermacher/Tema_Q-X3-Thinking-i1-GGUF: Quantization