© 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. 16723
    Prev
    Next
    INDEX
    Explanations

    Proper names

    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
    çļĦäººåľ¨
    -0.07
    unic
    -0.07
    umon
    -0.06
    locker
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    æ´»åĬ¨åľ¨
    -0.06
    åIJĮæł·
    -0.06
    زاÙħ
    -0.06
    åľ¨èIJ¥
    -0.06
    äººåľ¨
    -0.06
    POSITIVE LOGITS
    éļ¾å¾ĹçļĦ
    0.08
     Æ¡i
    0.07
     '".
    0.07
    หà¸Ļ
    0.07
     اÙĦعزÙĬز
    0.07
    liegen
    0.06
    ForResult
    0.06
     доÑĢогой
    0.06
    æĹłä¸Ĭ
    0.06
    spb
    0.06
    Activations Density 0.059%

    No Known Activations