© 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. 58876
    Prev
    Next
    INDEX
    Explanations

    gaussian beams

    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
     ìĹŃ
    -0.07
    rouw
    -0.07
    .prepend
    -0.07
     Rear
    -0.07
     disag
    -0.07
     irregular
    -0.06
    åºĶè¯ķ
    -0.06
    ÙĪضة
    -0.06
    æĺ¯åŃ¦æł¡
    -0.06
     tub
    -0.06
    POSITIVE LOGITS
     gaussian
    0.09
    aln
    0.08
    ga
    0.08
    à¹Īà¸Ńม
    0.08
    éļĻ
    0.08
    ä¿®
    0.08
    è¡°åĩı
    0.07
    aussian
    0.07
    ewidth
    0.07
    Ga
    0.07
    Activations Density 0.009%

    No Known Activations