© 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. 61617
    Prev
    Next
    INDEX
    Explanations

    list separators and code structure

    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
    å¯Įäºİ
    -0.08
    OGLE
    -0.08
    ADER
    -0.08
    aza
    -0.08
    èIJ¦
    -0.07
    entif
    -0.07
    è¿Ļ个æĸ¹æ³ķ
    -0.07
    бин
    -0.07
    иÑģÑĤÑĢа
    -0.07
    è¿Ļç§įæĸ¹æ³ķ
    -0.07
    POSITIVE LOGITS
    èche
    0.07
    pty
    0.07
    è¿Ľä¸ĢæŃ¥æİ¨è¿Ľ
    0.07
    osat
    0.07
    è¸ıãģ¿
    0.07
    uit
    0.07
    lott
    0.07
    anded
    0.07
    è¿Ľä¸ĢæŃ¥æݨåĬ¨
    0.07
    (_,
    0.07
    Activations Density 0.001%

    No Known Activations