© 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. 33826
    Prev
    Next
    INDEX
    Explanations

    numbers and code snippets

    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
     doss
    -0.07
    íݸ
    -0.07
     sympath
    -0.07
    ivist
    -0.06
     Compl
    -0.06
    åĴĮ西
    -0.06
    ×ķ×ŀר
    -0.06
    ulik
    -0.06
    <&
    -0.06
    ä¹ŁçŁ¥éģĵ
    -0.06
    POSITIVE LOGITS
    (exports
    0.07
    ç¥Ŀç¦ıä½ł
    0.07
    使èĩªå·±çļĦ
    0.07
    DataExchange
    0.07
    oreign
    0.07
    æ®ĸ
    0.07
    Nullable
    0.07
    ayload
    0.07
    LETTE
    0.07
    大浪
    0.07
    Activations Density 0.013%

    No Known Activations