© 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. 56482
    Prev
    Next
    INDEX
    Explanations

    more stuff, better operation, full life

    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
     latter
    -0.08
    ffel
    -0.08
    itÃł
    -0.07
    ilik
    -0.07
    ohner
    -0.07
    idades
    -0.07
    ׳×Ļ×Ķ
    -0.07
    æıĴä¸Ĭ
    -0.07
    udet
    -0.07
    iker
    -0.07
    POSITIVE LOGITS
     pula
    0.11
    urs
    0.06
    .TryParse
    0.06
    èĬ±æŶéĹ´
    0.06
    URS
    0.06
    orem
    0.06
    çIJ³å¨ľ
    0.06
    encil
    0.06
    Å¡n
    0.06
    ä¹Łæĺ¯æľĢ
    0.06
    Activations Density 0.094%

    No Known Activations