© 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. 41063
    Prev
    Next
    INDEX
    Explanations

    color names followed by 'and' or 'or'

    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
    åĽĽ
    -0.07
    çļĦ大
    -0.06
    çļĦå°ı
    -0.06
    äºĮ
    -0.06
     Stol
    -0.06
    -mark
    -0.06
    ä¼Ĭ
    -0.06
    ubin
    -0.06
    áĥ¨
    -0.06
    tra
    -0.06
    POSITIVE LOGITS
    第ä¸īç§į
    0.10
    第ä¸īæĿ¡
    0.09
    第ä¸īåIJį
    0.09
     enfin
    0.09
    ãģĿãģĹãģ¦
    0.09
    第ä¸īæĸ¹æĶ¯ä»ĺ
    0.08
    ôi
    0.08
    第ä¸ī个
    0.08
     infine
    0.08
    第ä¸īä½į
    0.08
    Activations Density 0.185%

    No Known Activations