© 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. 57365
    Prev
    Next
    INDEX
    Explanations

    wood products

    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
    ivity
    -0.10
    ï¸İ
    -0.09
    åĪ©æµ¦
    -0.08
    ault
    -0.07
    йÑĤ
    -0.07
    ä¸įå¦Ļ
    -0.07
    <|box_end|>
    -0.07
    ively
    -0.07
    èİ«æµĭ
    -0.07
     mức
    -0.07
    POSITIVE LOGITS
    è´¨çļĦ
    0.09
    pile
    0.09
    iness
    0.08
    人æ°ijåħ±åĴĮåĽ½
    0.08
    bine
    0.08
    lenme
    0.08
     ÑģобÑĸ
    0.08
    æ¢Ĩ
    0.07
    yla
    0.07
    fulness
    0.07
    Activations Density 0.022%

    No Known Activations