© 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. 18484
    Prev
    Next
    INDEX
    Explanations

    numbers, versions, or variables

    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
     ÙħÙĨÙĩÙħا
    -0.12
     Ambas
    -0.09
    æľī两ç§į
    -0.08
    à¸Ĺัà¹īà¸ĩสà¸Ńà¸ĩ
    -0.08
    umpt
    -0.08
    تÙĩÙħا
    -0.08
    è¿Ļ两ç§į
    -0.08
    å°ıæıIJ示
    -0.08
    reet
    -0.08
    ordi
    -0.07
    POSITIVE LOGITS
    —all
    0.10
    ãģ¨ãģĦãģ£ãģŁ
    0.09
    åħ¨éĥ¨
    0.09
     allemaal
    0.09
     all
    0.08
    è¿Ļä¸ī个
    0.08
    缺ä¸Ģä¸įåı¯
    0.08
    ãģĿãĤĮãģŀãĤĮãģ®
    0.08
    è¿Ļåĩłä¸ª
    0.08
    ä¸īèĢħ
    0.08
    Activations Density 0.047%

    No Known Activations