© 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. 9361
    Prev
    Next
    INDEX
    Explanations

    probability sequence

    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
    cir
    -0.07
    åľ¨ä¸ĢæĹģ
    -0.06
    å¿ĹæĪIJ
    -0.06
     un
    -0.06
    re
    -0.06
    edly
    -0.06
    Ì
    -0.06
    ”
    -0.06
    su
    -0.06
    à¥Į
    -0.06
    POSITIVE LOGITS
    请ä¸ĭè½½
    0.09
    otka
    0.09
    apel
    0.08
    essin
    0.08
    大åĬĽå®ŀæĸ½
    0.08
    _NB
    0.08
    æķĻèĤ²å¼ķ导
    0.08
    ä¸¥æł¼èIJ½å®ŀ
    0.08
    漫天
    0.08
    divider
    0.08
    Activations Density 0.002%

    No Known Activations