© 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. 1228
    Prev
    Next
    INDEX
    Explanations

    boolean conditions or exceptions

    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
    æľīä»Ģä¹ĪçĶ¨
    -0.07
    èĤ¡
    -0.07
     дип
    -0.07
    idth
    -0.06
    åİŁä½ĵ
    -0.06
    Offline
    -0.06
    ä¸Ńå¿ĥåĮ»éĻ¢
    -0.06
    bare
    -0.06
    è¢«åĽ°
    -0.06
    (dep
    -0.06
    POSITIVE LOGITS
    ë²Ķ
    0.08
     otherwise
    0.08
     Otherwise
    0.08
    Otherwise
    0.08
    èĭ¥éĿŀ
    0.08
    Tho
    0.08
    åIJ¦åĪĻ
    0.08
    èĭ¥ä¸įæĺ¯
    0.07
    ä¸įåĩº
    0.07
    vore
    0.07
    Activations Density 0.155%

    No Known Activations