© 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. 26411
    Prev
    Next
    INDEX
    Explanations

    default programming keywords

    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
    gak
    -0.08
     tÆ°á»Ŀng
    -0.07
    ewise
    -0.07
    æ±Ĥå®ŀ
    -0.07
    _requires
    -0.07
    _utils
    -0.07
     thuáºŃn
    -0.07
    _typeof
    -0.07
    WISE
    -0.07
    _locked
    -0.07
    POSITIVE LOGITS
     default
    0.08
    ä»£æĽ¿
    0.08
    é»ĺ认
    0.07
    default
    0.07
    é»ĺ认çļĦ
    0.07
    çħ§å¸¸
    0.07
    æĭŁ
    0.07
    áĢĢáĢº
    0.07
    åĭ¤
    0.07
    Default
    0.06
    Activations Density 0.009%

    No Known Activations