© 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. 60177
    Prev
    Next
    INDEX
    Explanations

    powers and mathematical forms

    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
    FUL
    -0.07
    éľ²æ°´
    -0.07
    Õ¡Õ°
    -0.07
    åĽĽæµ·
    -0.07
    äft
    -0.07
    bÃŃ
    -0.07
    tas
    -0.07
    uide
    -0.07
    ibri
    -0.07
    .average
    -0.07
    POSITIVE LOGITS
    æ·±æĮĸ
    0.08
    lific
    0.07
    bast
    0.07
    elv
    0.07
    äºijå³°
    0.07
    å½¢å¼ıçļĦ
    0.07
    è¿ŀåŁİ
    0.07
    æīĢæĮģ
    0.07
    å½¢
    0.07
     forms
    0.07
    Activations Density 0.004%

    No Known Activations