© 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. 40106
    Prev
    Next
    INDEX
    Explanations

    Created by

    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
     ÑĢолÑĮ
    -0.08
    /or
    -0.08
    eea
    -0.08
    èĢĮåIJİ
    -0.08
    å®ĥ们
    -0.08
    ë¶Ī
    -0.07
     Wan
    -0.07
    Ñģком
    -0.07
    åħ¶ä¸Ń
    -0.07
    ä¸Ģæĸ¹éĿ¢
    -0.07
    POSITIVE LOGITS
    ä¹Łæĺ¯å¦ĤæѤ
    0.11
    misc
    0.09
    éĥ¨åī¯
    0.09
    .createObject
    0.09
    æĪIJç«ĭäºİ
    0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    0.09
    idian
    0.09
    åĢĴæĺ¯
    0.08
    è§Ĵ度çľĭ
    0.08
    /lic
    0.08
    Activations Density 0.337%

    No Known Activations