Qwen3-14B

14B Qwen3 model quantized to 4-bit NF4; tested in OCEAN benchmarks

Neighborhood — ranked by edge-count

concept

Qwen3-1.7B
related_to
Smallest Qwen3 model tested; used in conscientiousness sweep example (Table 6)
Qwen3-4B
related_to
4B Qwen3 model tested in OCEAN benchmarks
Qwen3.5-9B
related_to
Smallest model tested as evolver; produces harness updates comparable to Claude Opus 4.6 on SkillsBench

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Qwen3-32Bconcept0.846
Weak-tier open-source model exhibiting both harness activation failure and adherence failure, with 25.1% skill-load rate
Qwen3-235B-A22Bconcept0.838
Large open-source model used as anchor agent and anchor evolver; illustrates benchmark-dependent evolver performance
Qwen2.5-VL-7Bconcept0.791
Base vision-language model used to instantiate ATLAS.
Qwen 3 0.6B Embeddingmethod0.776
Embedding model used to embed user messages for ridge regression analysis of persona drift causes
Qwen 35B (3B active params, score 4.38) outscores Hermes 405B (405B active params, score 1.75) by 2.5xfinding0.710
Parameters don't predict scores; 135x more parameters yields 60% lower score
LLaMA3.1-8Bconcept0.704
One of four LLMs selected for representation analysis; embedding dimension D=4096; used as demonstration model in scatter plots.
LLaMA3.1-70Bconcept0.678
One of four LLMs selected; larger model with D=8192 embedding dimension; analyzed across proportionally aligned layers.
Qwen 2.5 7B wellbeing probe: peak Cohen's d=3.5finding0.678
Strongest cross-family probe; explains clearer introspection in Qwen than Gemma