© 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. 28606
    Prev
    Next
    INDEX
    Explanations

    digits after equations

    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
    è²Į
    -0.08
    ijo
    -0.08
    /exp
    -0.07
     Approach
    -0.07
    elsen
    -0.07
    Æ°ng
    -0.06
    /stream
    -0.06
    utu
    -0.06
    ç¼ĺæķħ
    -0.06
    stein
    -0.06
    POSITIVE LOGITS
    reater
    0.07
    pery
    0.07
    æıIJéĨĴæĤ¨
    0.06
    enje
    0.06
     Domain
    0.06
    åĽ½åįİ
    0.06
    cce
    0.06
    ÑĢож
    0.06
    .VK
    0.06
    ĥĿ
    0.06
    Activations Density 0.122%

    No Known Activations