© 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. 6955
    Prev
    Next
    INDEX
    Explanations

    summarydefview

    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
    _SF
    -0.08
    iazza
    -0.08
     Nug
    -0.07
    fal
    -0.07
    åĬłå¼ºåŃ¦ä¹ł
    -0.07
    oghi
    -0.07
    oud
    -0.07
    iqu
    -0.07
    weeney
    -0.07
    icum
    -0.07
    POSITIVE LOGITS
    enh
    0.07
    ç¾İ好çļĦ
    0.07
    udel
    0.07
     parten
    0.07
     posse
    0.07
     genie
    0.07
    主æĮģ
    0.07
    reso
    0.07
    åIJĪ约
    0.07
     resa
    0.07
    Activations Density 0.263%

    No Known Activations