© 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. 24795
    Prev
    Next
    INDEX
    Explanations

    seeking clarification or understanding

    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
    æł¹æį®ä¸ªäºº
    -0.07
    æľ¬äººåľ¨
    -0.07
    åĵ½
    -0.07
    åĨ·åĨ·çļĦ
    -0.07
     REPLACE
    -0.07
    æīĢæıIJä¾ĽçļĦ
    -0.07
    ä½łèĩªå·±
    -0.07
    asl
    -0.06
    éĢļè¿ĩåIJĦç§į
    -0.06
    verno
    -0.06
    POSITIVE LOGITS
    çľĭçľĭåIJ§
    0.08
    çľĭçľĭ
    0.07
    ä¸Ģ举
    0.07
    端åĢª
    0.07
    åģļåĩĨå¤ĩ
    0.07
    ãģĵãĤĮãģĮ
    0.07
    顺便
    0.07
    èµ°åIJ§
    0.07
    à¸Ĭัà¸Ķ
    0.07
    )::
    0.06
    Activations Density 0.064%

    No Known Activations