© 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. 7044
    Prev
    Next
    INDEX
    Explanations

    picture 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
    Negative Logits
    à¯įà®ķ
    -0.11
    ê»ĺ
    -0.09
    istrator
    -0.09
    est
    -0.08
    ampton
    -0.08
    mits
    -0.07
    ä¸įæ¸Ŀ
    -0.07
    ê²IJ
    -0.07
    群ä¼ĹåĬŀå®ŀäºĭ
    -0.07
    каде
    -0.07
    POSITIVE LOGITS
     اÙĦØŃاÙĦ
    0.08
     halnya
    0.07
    ually
    0.07
     vivant
    0.07
    maker
    0.06
     маÑģлом
    0.06
     Ñģобой
    0.06
    iard
    0.06
    urity
    0.06
    o
    0.06
    Activations Density 0.026%

    No Known Activations