qwen3.5-4b/reasoning_pack
Qwen/Qwen3.5-4B · GSM8K (math reasoning)
Spearman ρ
0.540
Pearson r
0.726
n (held-out)
100
Features
10 helpful + 10 harmful
Cohen's d range: [+2.06, +2.16] / [−2.47, −2.06]
Discovered on: 50 GSM8K responses (raw Q/A)
Feature packs
Catalog
Each pack is a validated set of helpful + harmful SAE features discovered via contrastive correctness analysis. To appear here, a pack must pass Stage Gate 1 (Spearman ρ ≥ 0.30 on held-out data).
Validated
qwen3.6-35b-a3b/reasoning_pack
Qwen/Qwen3.6-35B-A3B · SuperGPQA (science/engineering)
Spearman ρ
0.522
Pearson r
0.537
n (held-out)
100
Features
10 helpful + 10 harmful
Cohen's d range: [+1.72, +1.84] / [−1.73, −1.36]
Discovered on: 50 SuperGPQA responses (thinking mode)
gemma-4-e4b/reasoning_pack
Google/Gemma-4-E4B · GSM8K (pending)
Spearman ρ
—
Pearson r
—
n (held-out)
—
Features
—
Cohen's d range: pending contrastive discovery
Discovered on: —
Contribute a pack
If you train a SAE on a new model + architecture and run Stage Gate 1 on a labeled benchmark, open a PR to the catalogs/ directory. Packs that meet the ρ ≥ 0.30 threshold on an independent held-out set will be merged and appear here. See the pack template for required fields.