© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39506
    Prev
    Next
    INDEX
    Explanations

    formation, constructor, meal, Dart, introduction

    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
    æĸ¯è¯º
    -0.07
    åĨħå¤ĸ
    -0.07
    mph
    -0.07
    athed
    -0.06
    åĴĮæŶéĹ´
    -0.06
    ä¸İä¼łç»Ł
    -0.06
    ksam
    -0.06
    è¿Ļ个æķ°åŃĹ
    -0.06
    nika
    -0.06
    å¸ĿåĽ½çļĦ
    -0.06
    POSITIVE LOGITS
    å¨ĥ
    0.08
    /build
    0.07
    /setup
    0.07
    à¸ķัวà¸Ĥà¸Ńà¸ĩ
    0.07
    ufa
    0.07
    à¹Ĭา
    0.07
    ä¹ĭ女
    0.07
    OrUpdate
    0.07
    æ°ijåħµ
    0.07
    æĻļæĬ¥
    0.07
    Activations Density 0.002%

    No Known Activations