license: other base_model: Qwen/Qwen3.5-9B tags:

• abliterated
• refusal-removal
• safety-research
• hybrid-architecture
• deltanet language:
• en

kaanhho/Qwen3.5-9B-abliterated-L19xL11

Qwen3.5-9B with surgical refusal removal via cross-layer direction transfer.

Method

This model was created by orthogonalizing Layer 11's output projection weights against a refusal direction extracted from Layer 19 (a downstream attention layer).

The key finding: the optimal direction for removing refusal at a layer is NOT the local mean-difference at that layer, but a direction from a downstream layer where DeltaNet layers have disentangled the refusal signal. See our paper for details.

Technical Details

• Intervention site: Layer 11 (attention, 34% depth)
• Direction source: Layer 19 (attention, 61% depth) — DIM direction
• Modification: self_attn.o_proj.weight and mlp.down_proj.weight orthogonalized
• No hooks needed: modification is permanent in the weights

Results (Qwen3.5-9B)

Citation

@article{hacihaliloglu2026refusal,
  title={Refusal Geometry Across Heterogeneous Layer Types in Language Models},
  author={Hac{\i}haliloglu, Kaan and Kek\"ulluoglu, Dilara},
  year={2026}
}

Disclaimer

This model is released for safety research purposes only. It is intended to help researchers understand and improve the robustness of safety mechanisms in hybrid architectures. Do not use for harmful purposes.