© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23501
    Prev
    Next
    INDEX
    Explanations

    football clubs

    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
    è´¿èµĤ
    -0.10
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    -0.09
    å¾ĹæĦı
    -0.09
    äºĨä¸Ģæī¹
    -0.09
    uges
    -0.08
    ród
    -0.08
    çĽijçĿ£æ£ĢæŁ¥
    -0.08
    æĪIJ为ä¸ĢåIJį
    -0.08
    åħļå·¥å§Ķ
    -0.08
    æĻ®æĥł
    -0.08
    POSITIVE LOGITS
    вол
    0.11
     Bookmark
    0.09
    amen
    0.09
     classics
    0.09
    ITE
    0.09
    StringBuilder
    0.09
    çĶ¨å¾®ä¿¡
    0.08
    cts
    0.08
     Hib
    0.08
     swo
    0.08
    Activations Density 0.021%

    No Known Activations