© 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. 19985
    Prev
    Next
    INDEX
    Explanations

    western shore

    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
    à¦Ļ
    -0.07
    /moment
    -0.07
    æµģåIJij
    -0.07
    åĪĨä¹ĭ
    -0.07
    åѦ
    -0.07
    åĿ¡
    -0.07
    èij
    -0.07
    xt
    -0.07
    ä¸ĢåIJ¬
    -0.07
    adero
    -0.07
    POSITIVE LOGITS
    ipas
    0.07
    &view
    0.07
    设计ä¸İ
    0.07
    IRST
    0.07
    æķĻèĤ²ä¸İ
    0.07
    azos
    0.07
    žÃŃ
    0.07
    èĩªå·±ä¸į
    0.07
    kos
    0.06
    pets
    0.06
    Activations Density 0.001%

    No Known Activations