© 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. 33941
    Prev
    Next
    INDEX
    Explanations

    Such

    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
     resh
    -0.07
    ogh
    -0.07
    oud
    -0.07
    жели
    -0.07
    aily
    -0.06
     sprink
    -0.06
    áĢ°áĢ¸
    -0.06
    ανε
    -0.06
    æľīæĦŁ
    -0.06
     pat
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.09
    ,DB
    0.08
    鲤
    0.07
    çĥĽåħī
    0.07
     Bu
    0.07
    æİĮæı¡çļĦ
    0.07
    ignan
    0.07
    对åħ¬åı¸çļĦ
    0.07
    ìĿ´íĬ¸
    0.07
    Bu
    0.07
    Activations Density 0.001%

    No Known Activations