© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31978
    Prev
    Next
    INDEX
    Explanations

    programming languages and tools

    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
    /logout
    -0.07
    禹
    -0.07
    éļ¾æ±Ĥ
    -0.07
     "/",
    -0.07
    åľ¨è¯»
    -0.07
    estate
    -0.06
     prerequisite
    -0.06
    é¡»çŁ¥
    -0.06
     '/',
    -0.06
    ?page
    -0.06
    POSITIVE LOGITS
    æĪĸåħ¶ä»ĸ
    0.08
    éģ¨
    0.07
    _checked
    0.07
    亨
    0.07
    à¹Īาà¸ĩ
    0.07
    azu
    0.07
     snippet
    0.07
    è¡ĮåĪĹ
    0.07
    身影
    0.07
    idamente
    0.07
    Activations Density 0.004%

    No Known Activations