© 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. 38773
    Prev
    Next
    INDEX
    Explanations

    numbers and patients

    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
    ĩ
    -0.08
    wart
    -0.08
    Appear
    -0.07
    åįĥéĩĮ
    -0.07
    omu
    -0.07
    oghi
    -0.07
    æĬĺåIJĪ
    -0.07
    主åŃIJ
    -0.07
    å¯ħ
    -0.07
    anter
    -0.07
    POSITIVE LOGITS
    .ed
    0.07
    ä¸įåIJĮç±»åŀĭ
    0.07
    q
    0.07
    å·¦åı³çļĦ
    0.07
    acons
    0.07
    åħ¶ä¸ŃåĮħæĭ¬
    0.07
    ilon
    0.07
    roker
    0.07
    atted
    0.06
    ãģ®ãģĨãģ¡
    0.06
    Activations Density 0.291%

    No Known Activations