© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64036
    Prev
    Next
    INDEX
    Explanations

    Given

    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
    äºĮå±Ĥ
    -0.08
    odash
    -0.07
    羣æŃ£æĪIJ为
    -0.07
    isode
    -0.07
    ếm
    -0.07
    ió
    -0.07
    ä¸Ģå±Ĥ
    -0.07
    ibar
    -0.07
    ç¼¥
    -0.07
    èĤ¯
    -0.07
    POSITIVE LOGITS
    óf
    0.08
    以ä¸ĭæĿ¡ä»¶
    0.08
    icked
    0.07
    種種
    0.07
    ç§įç§įåİŁåĽł
    0.07
    :f
    0.07
    ç§įç§į
    0.07
    Ùģعة
    0.07
    è§Ī
    0.06
    è¿ĻäºĽä¿¡æģ¯
    0.06
    Activations Density 0.069%

    No Known Activations