© 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. 58253
    Prev
    Next
    INDEX
    Explanations

    numbers following `it` or `an`

    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
    é¥ĭ
    -0.07
    رج
    -0.07
    zp
    -0.07
    _INITIALIZER
    -0.07
    è¿ĺæĺ¯åľ¨
    -0.07
    å²³éºĵ
    -0.07
    ivin
    -0.07
    é¦Ī
    -0.07
    kung
    -0.07
    ç´¡
    -0.07
    POSITIVE LOGITS
    laf
    0.07
    .overflow
    0.07
     dew
    0.07
    apus
    0.06
    ÑģÑĤÑĥпиÑĤÑĮ
    0.06
    _BOUND
    0.06
    éĿĴé¾Ļ
    0.06
     ê°ľ
    0.06
    åĩ¤
    0.06
    èĭŀ
    0.06
    Activations Density 0.002%

    No Known Activations