© 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. 3613
    Prev
    Next
    INDEX
    Explanations

    conditions or different phases

    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
    zog
    -0.07
     quals
    -0.07
    mage
    -0.07
     conforme
    -0.07
    trado
    -0.07
    aver
    -0.07
    otre
    -0.07
    åIJĮåŃ¦åľ¨
    -0.07
    天éķ¿
    -0.06
    vor
    -0.06
    POSITIVE LOGITS
    åĽĽä¸ªæĸ¹éĿ¢
    0.13
    ä¸ī个æĸ¹éĿ¢
    0.12
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.12
    两个æĸ¹éĿ¢
    0.12
    ä¸įåIJĮè§Ĵ度
    0.12
    åĩłä¸ªæĸ¹éĿ¢
    0.10
    å¤ļè§Ĵ度
    0.10
    两æĸ¹éĿ¢
    0.10
    个æĸ¹éĿ¢
    0.10
    çŃīæĸ¹éĿ¢è¿Ľè¡Į
    0.09
    Activations Density 0.010%

    No Known Activations