© 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. 45499
    Prev
    Next
    INDEX
    Explanations

    work, jobs, consultation, printing, delivery

    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
    loo
    -0.07
    丹
    -0.07
    ä¸Ģä¼Ĺ
    -0.07
    马åĪº
    -0.07
    禹
    -0.07
    umuz
    -0.06
     Supplementary
    -0.06
    ç«ĭåį³è´Ńä¹°
    -0.06
     Publishers
    -0.06
    åĬªåĬĽ
    -0.06
    POSITIVE LOGITS
    ç§įç±»
    0.07
    ãģĵãģª
    0.07
     shorter
    0.07
    è§ģå¾Ĺ
    0.07
    çĸijéļ¾
    0.07
     clientele
    0.07
    è´¨éĩı为
    0.07
    ÃŃž
    0.07
    mens
    0.07
    OfType
    0.07
    Activations Density 0.564%

    No Known Activations