© 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. 34713
    Prev
    Next
    INDEX
    Explanations

    function(`variable`)

    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
    æ®ĩ
    -0.08
    azzi
    -0.08
    olib
    -0.08
    -regexp
    -0.08
     Beij
    -0.08
    illaume
    -0.07
    wic
    -0.07
    ialog
    -0.07
    éģ®
    -0.07
    ör
    -0.07
    POSITIVE LOGITS
    ()'
    0.06
    ç¨ĭåºı设计
    0.06
    ä»»æĦı
    0.06
     function
    0.06
    æ·ĭæ¼ĵå°½
    0.06
    æ´»åĬ¨çŃī
    0.06
    ↵        ↵        ↵
    0.06
    æ³ķæĺ¯
    0.06
    è¿Ļ个åĵģçīĮ
    0.06
     سر
    0.06
    Activations Density 0.026%

    No Known Activations