© 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. 47784
    Prev
    Next
    INDEX
    Explanations

    dates and year ranges

    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
     whose
    -0.07
    elli
    -0.07
    ob
    -0.07
    äºĮ鼶
    -0.06
    æĸ¹éĿ¢çļĦ
    -0.06
    è¿ĻäºĽå¹´
    -0.06
    å±±æĻ¯åĮº
    -0.06
    è¿ijå¹´æĿ¥
    -0.06
    ir
    -0.06
    ноÑģ
    -0.06
    POSITIVE LOGITS
    pth
    0.08
    itchen
    0.08
    Äħc
    0.08
    ÑĴе
    0.08
    jel
    0.08
    ,__
    0.08
    -too
    0.08
    /color
    0.08
    -present
    0.07
    ä¿Ŀ驾
    0.07
    Activations Density 0.135%

    No Known Activations