© 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. 14472
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    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
    æĺ¯ä¸Ģç§įéĿŀ常
    -0.07
    åĮħåIJĥ
    -0.07
    _clause
    -0.07
    à¹Īวà¸ĩ
    -0.07
    metics
    -0.06
     Depart
    -0.06
    igham
    -0.06
    uari
    -0.06
    åŁºå±Ĥåħļ建
    -0.06
    åıĪéģĵ
    -0.06
    POSITIVE LOGITS
    dsn
    0.07
    æīĵåıij
    0.07
     programmes
    0.07
     Selección
    0.07
    交åı£
    0.07
    دÙĩ
    0.07
     겨
    0.07
    оÑģ
    0.07
    âng
    0.06
    roz
    0.06
    Activations Density 0.007%

    No Known Activations