© 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. 56083
    Prev
    Next
    INDEX
    Explanations

    wildland fires

    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
    isman
    -0.08
    iasi
    -0.08
    gettext
    -0.08
    ingleton
    -0.08
    chnet
    -0.07
    åĽ¾æĸ¯
    -0.07
    èŁ
    -0.07
    ä¸Ń大
    -0.07
    :ss
    -0.07
    HttpException
    -0.07
    POSITIVE LOGITS
    ä¸İåħ±
    0.07
    0.07
    ä¹ĭåĨħ
    0.07
    undert
    0.06
    æľĢåIJİåľ¨
    0.06
    ä¸įèĢģ
    0.06
    éĥ¨åĪĨç»ĦæĪIJ
    0.06
     киÑĢп
    0.06
     question
    0.06
    æ¯ı天æĻļä¸Ĭ
    0.06
    Activations Density 0.003%

    No Known Activations