© 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. 60070
    Prev
    Next
    INDEX
    Explanations

    chemical formula or syntax

    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
     #@
    -0.07
    Ùģس
    -0.07
    czyn
    -0.07
     COPYING
    -0.07
    ä¸ļåįıä¼ļ
    -0.07
    acan
    -0.06
    æĪij们çļĦ产åĵģ
    -0.06
    #@
    -0.06
    å°±æĭ¿
    -0.06
    δÎŃ
    -0.06
    POSITIVE LOGITS
    çīĪ
    0.08
    çīĪçļĦ
    0.08
    çīĪæľ¬çļĦ
    0.08
    èݱçī¹
    0.07
    ä¸įè´Ł
    0.07
    -version
    0.07
    æݨ
    0.06
    延
    0.06
     Tomorrow
    0.06
    kti
    0.06
    Activations Density 0.041%

    No Known Activations