© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37665
    Prev
    Next
    INDEX
    Explanations

    list closing bracket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    olog
    -0.07
    ron
    -0.07
    _constants
    -0.07
    åĶ
    -0.07
    没äºĭ
    -0.06
    inn
    -0.06
     sid
    -0.06
    ute
    -0.06
    owler
    -0.06
    æļĩ
    -0.06
    POSITIVE LOGITS
    åIJĦç§įåIJĦæł·
    0.08
    Liked
    0.08
    jde
    0.07
    ÛĮاÙĨ
    0.07
    zol
    0.07
    å¦Ĥæ½®
    0.07
    à¸Ńยà¹Īาà¸ĩà¸Ĺีà¹Ī
    0.07
    <|quad_start|>
    0.07
    éĢļè¿ĩè¿ĻäºĽ
    0.07
    zyma
    0.07
    Activations Density 0.003%

    No Known Activations