© 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. 51938
    Prev
    Next
    INDEX
    Explanations

    Leapster Explorer

    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
    Not in Any Lists

    No Comments

    Negative Logits
    atr
    -0.08
    _uniform
    -0.07
    ace
    -0.07
    稿件æĿ¥æºIJ
    -0.07
     Sound
    -0.07
    -0.06
    æ½®
    -0.06
    让
    -0.06
    è±¹
    -0.06
     Orient
    -0.06
    POSITIVE LOGITS
    ä¸įä¸ĭæĿ¥
    0.08
    éĻ¤æİī
    0.07
    alista
    0.07
    足çļĦ
    0.07
    件ä¸Ń
    0.07
    å¼ķè¿°
    0.07
    åħ´åĽ½
    0.07
    obat
    0.06
    ä»ĺåĩºäºĨ
    0.06
    erts
    0.06
    Activations Density 0.031%

    No Known Activations