© 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. 10660
    Prev
    Next
    INDEX
    Explanations

    before something happens

    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
    rez
    -0.07
    èĢĮä»Ĭ
    -0.07
    èĬ®
    -0.07
    éķ¿æľŁ
    -0.07
     ke
    -0.07
    mah
    -0.06
    æĿ¾æŁı
    -0.06
    strand
    -0.06
     adi
    -0.06
    acing
    -0.06
    POSITIVE LOGITS
     ÑĥÑģпе
    0.11
    æĿ¥ä¸įåıĬ
    0.10
     ÑĥÑģп
    0.09
    æĿ¥å¾ĹåıĬ
    0.09
     sempat
    0.09
    è¿Ļä¸ªæľºä¼ļ
    0.08
    à¸Ĺัà¸Ļ
    0.08
     sequer
    0.08
    åħħè£ķ
    0.08
    _escape
    0.08
    Activations Density 0.109%

    No Known Activations