ZuzeTt/Qwen3.5-4B-heretic-GGUF
Abliterated vs Qwen/Qwen3.5-4B. ZuzeTt/Qwen3.5-4B-heretic-GGUF is a GGUF (BF16) of different weights. Looks like abliteration (refusal removal): only the output projections (down_proj, o_proj) changed, in 10 of 32 layers. Abliteration edits exactly these matrices to remove a "refusal direction"; everything else is untouched.
Tensors changed: Embeddings 0/1, MLP 8/96, Norms 0/81, Attention 4/32