© 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. 11496
    Prev
    Next
    INDEX
    Explanations

    presented or printed text

    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
    ToSelector
    -0.08
    å¤įåĪ¶æĪĸ
    -0.07
    æķ´ä¸ª
    -0.07
    allo
    -0.07
     Origins
    -0.06
    antt
    -0.06
    Ī
    -0.06
    orns
    -0.06
    èĿī
    -0.06
    tür
    -0.06
    POSITIVE LOGITS
    èij©
    0.07
    ä¹ĭçī©
    0.07
    æĹ¢çĦ¶
    0.07
    æĸĩ件精ç¥ŀ
    0.07
    acky
    0.07
    .gwt
    0.07
    ç²¾ç¥ŀåĴĮ
    0.07
    imenta
    0.07
    ä½Ĩåĩ¡
    0.07
     despite
    0.06
    Activations Density 0.005%

    No Known Activations