© 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. 6004
    Prev
    Next
    INDEX
    Explanations

    O'Brien, RIA, Wrike

    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
    èĢģå¦Ī
    -0.11
    rais
    -0.10
    illo
    -0.10
     brace
    -0.09
    DBG
    -0.09
    èĸĦå¼±
    -0.09
    ä¹°ä¸ľè¥¿
    -0.09
    åŀ¢
    -0.09
    åIJĦæł·
    -0.09
    ilon
    -0.09
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.10
    aceous
    0.10
    ester
    0.08
    hood
    0.08
    QUEST
    0.08
    liness
    0.07
    اء
    0.07
    /blue
    0.07
    Trad
    0.07
    ance
    0.07
    Activations Density 0.002%

    No Known Activations