© 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. 34778
    Prev
    Next
    INDEX
    Explanations

    rounding to nearest integer or ten

    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
    à¸ļà¸Ķี
    -0.08
    çĽ¸çŁ¥
    -0.08
    imbra
    -0.08
    .GetAsync
    -0.08
    åıĮåŁİ
    -0.07
    æĹłéĹ´
    -0.07
    ç´¢
    -0.07
     unins
    -0.07
     Burke
    -0.07
    ensively
    -0.07
    POSITIVE LOGITS
     rounding
    0.07
     ±
    0.06
    æĸ¹æ³ķè¿Ľè¡Į
    0.06
    ìŁģ
    0.06
     bias
    0.06
     errors
    0.06
     toward
    0.06
     towards
    0.06
    å°ĸ
    0.06
     Errors
    0.06
    Activations Density 0.013%

    No Known Activations