© 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. 37482
    Prev
    Next
    INDEX
    Explanations

    functional component, class, hooks, stack, iterative

    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
    igno
    -0.07
    bole
    -0.07
    榴
    -0.07
     garn
    -0.07
    ieb
    -0.06
    åѤç«ĭ
    -0.06
    éĽªä¸Ń
    -0.06
    æİ
    -0.06
    ä¹į
    -0.06
    æĹłå¼Ĥè®®
    -0.06
    POSITIVE LOGITS
     instead
    0.08
    ä»£æĽ¿
    0.08
    æĽ¿ä»£
    0.08
    ĶĦ
    0.08
    è¿Ń代
    0.08
     Instead
    0.08
    instead
    0.08
     بدÙĦاÙĭ
    0.08
    æĶ¹æĪIJ
    0.07
     ITER
    0.07
    Activations Density 0.010%

    No Known Activations