© 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. 13698
    Prev
    Next
    INDEX
    Explanations

    . 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
    ä¿ĿæĮģçĿĢ
    -0.07
    ers
    -0.06
    ä¿ĿæĮģäºĨ
    -0.06
    etty
    -0.06
    abat
    -0.06
    å¼ĢåIJ¯äºĨ
    -0.06
    หมาย
    -0.06
    -community
    -0.06
    æīĢåľ¨åľ°åĮº
    -0.06
     community
    -0.06
    POSITIVE LOGITS
    rollo
    0.08
    ä¸įè¡ĮäºĨ
    0.08
    quire
    0.07
    RAS
    0.07
    лÑıми
    0.07
    gues
    0.07
    à¹Ģสีย
    0.07
    æ´»çļĦ
    0.07
     Tiong
    0.07
    nü
    0.07
    Activations Density 0.021%

    No Known Activations