© 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. 4692
    Prev
    Next
    INDEX
    Explanations

    html, css, javascript delimiters

    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
    èĢħæĺ¯
    -0.07
    iter
    -0.07
    "><!--
    -0.07
    æīĢä½ľ
    -0.07
    æĿĥè¯ģ
    -0.07
    tier
    -0.07
    olik
    -0.07
    undai
    -0.07
    ighter
    -0.07
     multer
    -0.07
    POSITIVE LOGITS
    æķ·
    0.07
    åĴĮå¸ĮæľĽ
    0.07
    prest
    0.06
     sart
    0.06
    åħĭ
    0.06
    apu
    0.06
    à¸ł
    0.06
    ç¾½
    0.06
    _ACTIVE
    0.06
    нок
    0.06
    Activations Density 0.130%

    No Known Activations