© 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. 7277
    Prev
    Next
    INDEX
    Explanations

    large quantities/numbers

    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
    elsey
    -0.07
    anse
    -0.07
    hof
    -0.07
    idot
    -0.07
    -wrap
    -0.07
    _broadcast
    -0.07
    kunde
    -0.07
     pylab
    -0.07
     funky
    -0.07
    abant
    -0.07
    POSITIVE LOGITS
    å·¥ä½ľéĩı
    0.07
    åī
    0.07
     CPU
    0.06
     computational
    0.06
     lente
    0.06
    eload
    0.06
    edel
    0.06
    eded
    0.06
    è®¤çľŁå®ĮæĪIJ
    0.06
     Count
    0.06
    Activations Density 0.001%

    No Known Activations