© 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. 701
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

    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
    anÃŃa
    -0.07
    okens
    -0.07
    没æľīæŶéĹ´
    -0.07
    oge
    -0.07
    åľ¨è¡ĮåĬ¨
    -0.06
    udir
    -0.06
    edis
    -0.06
    chan
    -0.06
    æĦıæĸĻ
    -0.06
    é¢ĦæľŁçļĦ
    -0.06
    POSITIVE LOGITS
    lant
    0.08
    纽带
    0.08
    çµIJãģ³
    0.07
    åħ¶ä¸İ
    0.07
    IfNeeded
    0.07
    andro
    0.07
     ÙĪتش
    0.07
    à¹Ģรà¸Ļ
    0.07
    oley
    0.07
    RICS
    0.07
    Activations Density 0.002%

    No Known Activations