© 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. 45336
    Prev
    Next
    INDEX
    Explanations

    one 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
    éĤ£äºĽ
    -0.09
    ÙĪÙĦÙĬØ©
    -0.08
    éĤ£äºĽäºº
    -0.07
     ÑģпÑĢаведли
    -0.07
    å±ķçİ°åľ¨
    -0.06
    acca
    -0.06
    没æľīä¸Ģ个
    -0.06
    åIJĦåľ°çļĦ
    -0.06
    fus
    -0.06
    rase
    -0.06
    POSITIVE LOGITS
    æĪĸå¤ļ个
    0.09
    æĪĸå¤ļ
    0.09
     davon
    0.09
     nanti
    0.09
     ervan
    0.08
    /all
    0.08
    å¿ħãģļ
    0.08
     ÙħÙĨÙĩÙħا
    0.08
     اÙĦآخر
    0.08
    åĴĮäºĮ
    0.08
    Activations Density 0.060%

    No Known Activations