© 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. 13015
    Prev
    Next
    INDEX
    Explanations

    organizational units and technical terms

    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
    äºĮ人
    -0.09
    ä»ĸä¿©
    -0.07
    两人çļĦ
    -0.07
    äºĮ人çļĦ
    -0.07
    两人
    -0.07
    ainment
    -0.06
    rant
    -0.06
    è¿Ļ两
    -0.06
    åĪĨæ°´
    -0.06
    αÏĥία
    -0.06
    POSITIVE LOGITS
     various
    0.12
    æ¯ıä¸Ģç§į
    0.12
    æ¯ıç§į
    0.12
    åIJĦç§į
    0.11
    åIJĦç§įä¸įåIJĮçļĦ
    0.11
    åĪĨåĪ«
    0.10
    ä¸įåIJĮç±»åŀĭçļĦ
    0.10
     ÑĢазлиÑĩнÑĭÑħ
    0.10
    åIJĦ種
    0.10
    以ä¸ĭåĩłç§į
    0.10
    Activations Density 0.733%

    No Known Activations