© 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. 57423
    Prev
    Next
    INDEX
    Explanations

    finding an answer

    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
    ấc
    -0.07
    anny
    -0.07
     sweep
    -0.07
    ://'
    -0.07
    _THRESH
    -0.07
    åºĬ
    -0.07
    quil
    -0.07
    æĭ¥
    -0.07
    thead
    -0.07
     sweeping
    -0.07
    POSITIVE LOGITS
    WithContext
    0.07
    ahkan
    0.07
    /result
    0.07
    æ¯ıæĹ¥ä¸Ģ
    0.07
    ständen
    0.07
    Express
    0.06
    INAS
    0.06
    stdarg
    0.06
    shire
    0.06
    å¿ĺ
    0.06
    Activations Density 0.003%

    No Known Activations