© 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. 16648
    Prev
    Next
    INDEX
    Explanations

    class names in code

    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
    é£ĵé£İ
    -0.08
    ì§ķ
    -0.07
    /../
    -0.07
    indent
    -0.07
     nhiêu
    -0.07
    åĴĮ建议
    -0.06
    æĥħæĦ¿
    -0.06
    ×Ŀ
    -0.06
    itt
    -0.06
     Ban
    -0.06
    POSITIVE LOGITS
    èche
    0.08
    ãĥ¼ãĤº
    0.08
    bis
    0.07
    iou
    0.07
    alan
    0.07
    _INITIALIZER
    0.07
    angelo
    0.06
    åIJĦæĸ¹éĿ¢
    0.06
    ukes
    0.06
    bres
    0.06
    Activations Density 0.100%

    No Known Activations