© 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. 29450
    Prev
    Next
    INDEX
    Explanations

    in the

    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
     behalf
    -0.15
    bject
    -0.11
     occasions
    -0.10
     occasion
    -0.10
    çŀ¬
    -0.10
    occasion
    -0.09
    /in
    -0.09
    /off
    -0.09
    ÑĢод
    -0.09
     ÑģайÑĤе
    -0.09
    POSITIVE LOGITS
     on
    0.10
     عÙĦÙī
    0.10
    顾èĻij
    0.10
    纳ç¨İ人
    0.09
     onComplete
    0.09
     trên
    0.09
    нÑĮ
    0.09
    æ²ī
    0.09
    两项
    0.09
    paren
    0.08
    Activations Density 0.317%

    No Known Activations