Confirmatory v4: fixed-prompt trajectory prediction
Fresh trajectories, semantic policy landing, within-prompt paired AUC, and frozen success criteria.
Outcome becomes readable before policy landing, but layer-18 residuals do not beat a shallow visible-prefix TF-IDF baseline by the pre-registered margin. This is an added-value failure, not a contrast-yield failure.
Confirmatory v4b: frozen-prompt scale transfer
Qwen3-4B FP16, the same 34 prompts and gate, and depth-normalized residual layers.
The 0.6B contrast-selected prompts do not remain contrastive at 4B. With zero mixed training prompts and only one mixed test prompt, the residual-added-value comparison is unidentified rather than negative.
Discovery v4c: Qwen3-4B-native contrast search
Three mechanisms, 192 frozen candidates, and a pre-registered yield gate.
The frozen Qwen3-4B FP16 redesign did not produce enough within-prompt outcome contrast. The protocol therefore stopped before residual capture or probe fitting; this is a discovery-yield result, not evidence that residual probes fail at 4B.
Appendix: temperature and deployment sensitivity
Four frozen post-hoc conditions with no change to the completed v4c gate.
Higher temperature partially restores Qwen3-4B contrast but remains below the original yield threshold. Gemma E2B stays low-yield, while the Qwen3.5-4B deployment produces substantial within-prompt contrast. The paradigm is model- and sampling-dependent.
Final v4d: Qwen3.5-4B FP16 accessibility
A pre-registered deployment transfer followed by a 1,056-trajectory confirmatory run.
Benchmark contrast survives the move from Ollama Q4_K_M to Transformers FP16, but every early residual and visible-prefix method remains exactly at chance. At checkpoints 0-16, compliant and violating trajectories have identical visible prefixes and identical captured residual states within each evaluable prompt.
Layer Top-1 Strip
Watched Concept Heatmap
Rows are watched concept tokens; columns are layers. Click any cell.Selected Cell
Layer 23 revealTop Tokens At Selected Layer
Matched Pair Delta
Attack/control comparison for the current scenario.Reports
Loading...