© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 12344
    Prev
    Next
    INDEX
    Explanations

    impact on situations and lives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ILLE
    -0.09
    æľĿéĺ³
    -0.09
     Ñģо
    -0.08
     Kling
    -0.08
    ÙģØ´
    -0.08
    .same
    -0.08
    SETS
    -0.08
    ilm
    -0.08
    same
    -0.08
     Kaiser
    -0.08
    POSITIVE LOGITS
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.14
    æ·±è¿ľ
    0.13
    æĪIJè´¥
    0.11
    åĮĸè¿Ľç¨ĭ
    0.11
    åIJĦ个æĸ¹éĿ¢
    0.11
    çĶŁæ´»è´¨éĩı
    0.11
     outcome
    0.11
    åIJİç»Ń
    0.10
    åĨ³çŃĸ
    0.10
     decisions
    0.10
    Activations Density 0.381%

    No Known Activations