© 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. 27548
    Prev
    Next
    INDEX
    Explanations

    finding roots of 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
    avin
    -0.07
    é¼İ
    -0.07
     amalg
    -0.06
    年建
    -0.06
    浩
    -0.06
    æŁIJç§į
    -0.06
    é¢ł
    -0.06
    fit
    -0.06
    çŀŃ
    -0.06
    smooth
    -0.06
    POSITIVE LOGITS
    idler
    0.08
    ä¸Ģ个个
    0.08
    -flash
    0.08
    Released
    0.07
    alang
    0.07
    ums
    0.07
    à®´à¯ģ
    0.07
    -null
    0.07
    edList
    0.07
    kal
    0.07
    Activations Density 0.006%

    No Known Activations