© 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. 64040
    Prev
    Next
    INDEX
    Explanations

    XML or WXML tags

    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
    åıĮèĸª
    -0.08
    anax
    -0.08
    æīĵéĢłæĪIJ
    -0.07
    usah
    -0.07
    游è¡Į
    -0.07
    æ¥
    -0.07
    onnier
    -0.07
    पà¥į
    -0.07
    anches
    -0.07
    å»ĬåĿĬ
    -0.07
    POSITIVE LOGITS
     Zhejiang
    0.07
     Campus
    0.07
    æł¡åĨħ
    0.07
    ump
    0.07
    ver
    0.07
     campus
    0.06
    èĮħ
    0.06
    ç»įåħ´
    0.06
    -hooks
    0.06
    æĭŁ
    0.06
    Activations Density 0.006%

    No Known Activations