© 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. 33686
    Prev
    Next
    INDEX
    Explanations

    median calculation

    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
    éĿ¢ç§¯çļĦ
    -0.07
    è®´
    -0.07
    gis
    -0.07
    åī²åIJĪ
    -0.07
    éĿ¢ç©į
    -0.07
    鬣
    -0.07
    arat
    -0.07
    æ¼³
    -0.07
    ابع
    -0.07
     volume
    -0.07
    POSITIVE LOGITS
    èĢ³
    0.07
    太é«ĺ
    0.07
    æľĢé«ĺçļĦ
    0.07
     envies
    0.07
     reigning
    0.07
    agro
    0.07
    ä¿®
    0.07
    æss
    0.07
    ä¿¡ç®±
    0.07
    ä¹ĭé«ĺ
    0.07
    Activations Density 0.007%

    No Known Activations