© 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. 13405
    Prev
    Next
    INDEX
    Explanations

    familiar with concepts

    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
    ä½ľä¸ļæŶ
    -0.07
    arle
    -0.07
    åijĹ
    -0.07
    гани
    -0.06
    æħij
    -0.06
    ÑģÑĤен
    -0.06
    ding
    -0.06
    ä½ķçŃī
    -0.06
    bah
    -0.06
    éĽĨä¸ŃçļĦ
    -0.06
    POSITIVE LOGITS
    ooks
    0.08
    æĪIJ为ä¸ĢåIJį
    0.08
    çļĦæľĭåıĭåı¯ä»¥
    0.07
    _OUTPUT
    0.07
     lâu
    0.07
    并å¸ĮæľĽ
    0.07
    è¡Įä¸ļåĬ¨æĢģ
    0.07
    lig
    0.07
    请åĪ°
    0.07
    åĨħ容æľī
    0.07
    Activations Density 0.033%

    No Known Activations