© 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. 13682
    Prev
    Next
    INDEX
    Explanations

    derivative of

    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¢ĸ
    -0.07
    桥头
    -0.07
    _FUNC
    -0.07
    orten
    -0.07
    ç©İ
    -0.07
    çī½
    -0.07
    shal
    -0.07
    cardo
    -0.07
    çīµ
    -0.07
    举è¡ĮäºĨ
    -0.07
    POSITIVE LOGITS
    æģĴå®ļ
    0.09
    æģĴ
    0.08
    dee
    0.07
    .constant
    0.07
    /constants
    0.07
    iace
    0.07
    leigh
    0.06
    éļ·
    0.06
    æıIJåıĸ
    0.06
    满天
    0.06
    Activations Density 0.006%

    No Known Activations