© 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. 21263
    Prev
    Next
    INDEX
    Explanations

    numbers followed by symbols or letters

    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
    羣çļĦ
    -0.08
    ثرة
    -0.07
    razier
    -0.07
    most
    -0.07
    onas
    -0.07
    æĪIJç«ł
    -0.07
    ç§ĭæľĪ
    -0.07
    ocks
    -0.07
    اÙĨØ´
    -0.07
    делÑĭ
    -0.06
    POSITIVE LOGITS
    uah
    0.08
    ä¸ĭåIJĮ
    0.07
    edException
    0.07
    inkin
    0.07
     example
    0.07
    arnos
    0.07
    ä¾ĭ
    0.07
    nard
    0.06
    оÑĢÑĤ
    0.06
    _CLIP
    0.06
    Activations Density 0.063%

    No Known Activations