© 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. 15555
    Prev
    Next
    INDEX
    Explanations

    that

    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
    ä½łæľī没æľī
    -0.08
    åı¥
    -0.07
    åĪļ好
    -0.07
    rific
    -0.07
    orest
    -0.06
    ä¼ļä¸įä¼ļ
    -0.06
    æĹłçĸij
    -0.06
    å°±éĿŀ常
    -0.06
    æĺ¯åIJ¦èĥ½å¤Ł
    -0.06
    åĪļåĪļ
    -0.06
    POSITIVE LOGITS
     only
    0.09
    è¿Ļæĺ¯ä¸Ģ个
    0.09
    è¿Ļåıªæĺ¯
    0.08
    è¿Ļæĺ¯ä¸ª
    0.08
    è¿ĻäºĽéĥ½æĺ¯
    0.08
     there
    0.08
    è¿Ļæĺ¯
    0.08
    æľ¬é¢ĺçŃĶæ¡Ī
    0.08
    è¿Ļæĺ¯ä¸Ģç§į
    0.08
     лиÑĪÑĮ
    0.08
    Activations Density 0.067%

    No Known Activations