© 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. 59130
    Prev
    Next
    INDEX
    Explanations

    yes, agreeing

    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
    Not in Any Lists

    No Comments

    Negative Logits
    зон
    -0.10
    æīĢæıIJä¾Ľ
    -0.10
    ä¸įå¾Ĺä¸į
    -0.10
     Äijâu
    -0.09
    ym
    -0.09
    ä¸ĢåIJį
    -0.09
    ä¸į妨
    -0.09
    年度
    -0.09
    uish
    -0.08
    wick
    -0.08
    POSITIVE LOGITS
    nock
    0.09
    æĪijä»¬åľ¨
    0.09
    æĪijä¹Ł
    0.09
    ç§ģãĤĤ
    0.08
    æľīä¸ĢäºĽ
    0.08
    没éĶĻ
    0.08
    ä¸İåIJ¦
    0.08
     Agree
    0.08
    æĺ¯æľī
    0.08
    æĪij们çļĦ
    0.08
    Activations Density 0.038%

    No Known Activations