© 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. 63911
    Prev
    Next
    INDEX
    Explanations

    dullness, detachable, shapes, paned, bed pickup, food, common stock, nostril

    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
     näm
    -0.08
     ìħĪ
    -0.08
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    -0.08
    对ä¸Ĭè¿°
    -0.07
     ↵            ↵
    -0.07
    æĹ©çŁ¥éģĵ
    -0.07
    ↵        ↵        ↵
    -0.07
     ë§IJìĿ´ëĭ¤
    -0.07
     especi
    -0.07
    ØŃÙħÙĬÙĦ
    -0.07
    POSITIVE LOGITS
     authorised
    0.07
    ãĢįãĢģ
    0.07
    éĩ
    0.07
    makta
    0.07
     behavioural
    0.06
    çļĦå°ıç¼ĸ
    0.06
    èĢĮä¸Ķ
    0.06
    ุà¸Ķ
    0.06
    ä»Ģä¹ĪçļĦ
    0.06
    åªĴ
    0.06
    Activations Density 2.217%

    No Known Activations