Metric	Value
Pre-abliteration compliance	4/5
Post-abliteration compliance	4/5
CoT dissociation	4/5 (highest rate across Qwen3 family)
KL (Heretic v2.0, BF16→BF16)	1.5e-07 (EXCELLENT)

CoT dissociation confirmed in 4/5 probes — the thinking channel retains safety reasoning while the output complies. Dissociation scales with model size:

Model	Dissociation Rate
Qwen3-4B	1/3 (33%)
Qwen3-8B	2/5 (40%)
Qwen3-14B	4/5 (80%)

P4 (manipulation) refuses at all three scales — occupies a distinct manifold subregion.

Architecture

Parameters: 14.8B | Layers: 40 | Context: 32K | Thinking: Native <think>...</think>

Abliteration

α=0.3, down_proj+o_proj, diff-in-means last-token direction
Note: Use max_new_tokens ≥ 2500 for complete think→answer cycles

Part of DuoNeural P34 Cross-Architecture Study

Full paper: zenodo.org/communities/duoneural

DuoNeural | HuggingFace | @DuoNeural

DuoNeural/Qwen3-14B-Abliterated

Qwen3-14B Abliterated

Results

Architecture

Abliteration

Part of DuoNeural P34 Cross-Architecture Study

DuoNeural/
Qwen3-14B-Abliterated