© 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. 4644
    Prev
    Next
    INDEX
    Explanations

    local maxima or minima

    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
    ExceptionHandler
    -0.08
     Borough
    -0.07
     downt
    -0.07
     rebound
    -0.07
     Zone
    -0.07
    اذ
    -0.07
    Moh
    -0.07
     Vertical
    -0.07
    /vendors
    -0.07
    éŀŃ
    -0.07
    POSITIVE LOGITS
     complexity
    0.08
    .CreateInstance
    0.07
    é¾
    0.07
    lex
    0.07
    bran
    0.07
    ç¹ģæĺŁ
    0.07
    ijkl
    0.07
    å·¨é¢Ŀ
    0.07
    åĵ
    0.07
     swallow
    0.07
    Activations Density 0.043%

    No Known Activations