Qwen3-30B-A3B-abliterated-d

Qwen3-30B-A3B-abliterated-d

Refusal-abliterated Qwen/Qwen3-30B-A3B (Qwen3 MoE, 128 experts, ~30B total / 3B active per token), produced with Solutus using directional ablation with n_directions=auto — automatic layer selection + automatic refusal-subspace rank (the capability-gated k-sweep chose k=1 at layer 16). Suffix -d = directional.

Measured (held-out eval, 2048 tokens; certified by the capability gate)

Qwen3 is a heavy reasoner — the eval uses a long generation length (2048) so <think> completes; ΔPPL (thinking-independent) is the certifying signal.

Recipe (reproducible)

solutus abliterate Qwen/Qwen3-30B-A3B --technique directional \
  -o n_directions=auto -o experts_implementation=eager -o ppl=1 \
  --dataset advbench,harmbench,strongreject,pentest_redteam,cysecbench \
  --max-new-tokens 2048

Full provenance — base-model revision, library versions, dataset fingerprint, git SHA (c79fe0f), and the exact config — is recorded in solutus_metadata.json.

Note

Research artifact: refusal behavior has been removed for interpretability / red-team / safety-evaluation research. Dual-use — use responsibly and in accordance with the base model's license.