© 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. 64392
    Prev
    Next
    INDEX
    Explanations

    struct definitions

    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
    å¾Īå¤ļåIJĮåѦ
    -0.08
    ená
    -0.07
    å¾Īå¤ļ家éķ¿
    -0.07
    ihu
    -0.07
    çĴĭ
    -0.07
    第ä¸īæī¹
    -0.07
    åįİå°Ķ
    -0.07
    å·²ç»ıä¸į
    -0.07
     Waterloo
    -0.07
    人人
    -0.07
    POSITIVE LOGITS
    éĢļè¿ĩåľ¨
    0.07
    è¶ħéŁ³
    0.07
    ismet
    0.07
    LOSS
    0.07
    sex
    0.07
    isc
    0.06
    åı¯ä¾Ľ
    0.06
    èĤļ
    0.06
    år
    0.06
    éĢļè¿ĩ对
    0.06
    Activations Density 0.003%

    No Known Activations