© 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. 39970
    Prev
    Next
    INDEX
    Explanations

    programming keywords and symbols

    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
    ogn
    -0.08
    说æĿ¥
    -0.07
    SY
    -0.07
    elaar
    -0.07
    odus
    -0.07
    pf
    -0.07
    opes
    -0.07
    é£İåı£
    -0.07
    edi
    -0.06
    (&(
    -0.06
    POSITIVE LOGITS
     again
    0.08
    åĩłåı¥
    0.08
    again
    0.07
     Again
    0.07
     ÙħÙĨا
    0.07
    apiro
    0.07
    azo
    0.07
    ä»Ĭ度ãģ¯
    0.07
    Again
    0.07
    OVA
    0.07
    Activations Density 0.098%

    No Known Activations