© 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. 47535
    Prev
    Next
    INDEX
    Explanations

    data types (String, Number, integer)

    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
    à¯įà®ķ
    -0.08
    _permission
    -0.08
    çļĦå·¥ä½ľä¸Ń
    -0.07
    evin
    -0.07
    /DTD
    -0.07
    è¿ĶåĽŀ顶éĥ¨
    -0.07
    wick
    -0.07
    cape
    -0.07
    æĻ¶æĻ¶
    -0.07
    uess
    -0.07
    POSITIVE LOGITS
    ább
    0.07
    er
    0.07
    vlak
    0.07
    æĪIJé¾Ļ
    0.07
    èħĬæľĪ
    0.07
    PS
    0.07
    بÙĦ
    0.07
    aÄĩ
    0.07
     embr
    0.06
    ÑģÑĭл
    0.06
    Activations Density 0.008%

    No Known Activations