© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 708
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    Negative Logits
    é
    -0.08
    CurrentValue
    -0.08
    oulos
    -0.07
    代çIJĨ
    -0.07
    é¡¹çĽ®åľ¨
    -0.07
    ä½¼
    -0.07
    osaic
    -0.07
    é¡¹çĽ®åĴĮ
    -0.07
    #elif
    -0.07
    missing
    -0.07
    POSITIVE LOGITS
     باÙĦØ´
    0.07
    ataloader
    0.07
    èĻļ
    0.07
    arcy
    0.06
    CP
    0.06
    tty
    0.06
    джеÑĢ
    0.06
    MainThread
    0.06
    acan
    0.06
    wayne
    0.06
    Activations Density 0.099%

    No Known Activations