© 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. 802
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Spicer
    -0.07
    äºĭæĪIJ
    -0.07
    eyer
    -0.07
    ehme
    -0.06
    好人
    -0.06
    arts
    -0.06
    满æĦı
    -0.06
     brig
    -0.06
    azzi
    -0.06
    ()._
    -0.06
    POSITIVE LOGITS
    ä¹ĭæľĢ
    0.07
    DIFF
    0.07
    人ä¸ĸ
    0.07
    itm
    0.07
    ÙĩاÙĨ
    0.07
    Blob
    0.07
    æľ¬å¸ĸ
    0.07
    ä¸İåĽ½åĨħ
    0.07
    äub
    0.07
    :http
    0.07
    Activations Density 0.000%

    No Known Activations