© 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. 13686
    Prev
    Next
    INDEX
    Explanations

    HKCR or WM_GETRECT

    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
    å¥Īä½ķ
    -0.07
    ikkert
    -0.07
    ä¸Ńå¿ĥåĮ»éĻ¢
    -0.07
    åIJĦè¡Į
    -0.07
    åįĩåĢ¼
    -0.07
    éĶ¦æ¶Ľ
    -0.07
    èĭ¦è¾£
    -0.06
    ä¸įåı¯æĢĿè®®
    -0.06
    unner
    -0.06
    äºijéľĦ
    -0.06
    POSITIVE LOGITS
    tek
    0.07
    opf
    0.07
    çĤ³
    0.07
    ä¸ĢæĿij
    0.07
    []{"
    0.06
    娱
    0.06
    æĺĵ
    0.06
     priori
    0.06
    ä¸ĢçļĦ
    0.06
    kao
    0.06
    Activations Density 0.428%

    No Known Activations