© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62957
    Prev
    Next
    INDEX
    Explanations

    heterogeneous group of disorders/diseases

    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
    两次
    -0.07
    ç»ıæµİä¸İ
    -0.07
    çļĦä¸Ģå®ļ
    -0.07
    两ä¸į误
    -0.06
    鼷æĸ¯
    -0.06
    alap
    -0.06
    éĩijå±±
    -0.06
    åºŁ
    -0.06
     Economy
    -0.06
    olib
    -0.06
    POSITIVE LOGITS
    å¤ļæł·çļĦ
    0.11
    ç§įç±»ç¹ģå¤ļ
    0.11
    åĮħæĭ¬äºĨ
    0.11
    æ³ĽæĮĩ
    0.10
     diverse
    0.10
     encompass
    0.10
     encompasses
    0.10
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.10
    å¤ļæł·
    0.10
     ranging
    0.09
    Activations Density 0.224%

    No Known Activations