© 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. 60502
    Prev
    Next
    INDEX
    Explanations

    call or cell

    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
    æ°ijäºĭè¡Į为
    -0.08
     Maur
    -0.08
    æłij人
    -0.08
    ä¸įè°ĥ
    -0.07
    è¡
    -0.07
    åľĪ
    -0.07
    LLLL
    -0.07
    .nlm
    -0.07
    _tel
    -0.07
    åľĪçļĦ
    -0.07
    POSITIVE LOGITS
    æł¼åŃIJ
    0.09
     격
    0.08
     practitioners
    0.07
     incremental
    0.07
    каÑģ
    0.07
    åįļ大
    0.07
    æł¼
    0.07
    éĺµ
    0.07
    egel
    0.07
    tus
    0.07
    Activations Density 0.005%

    No Known Activations