© 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. 37696
    Prev
    Next
    INDEX
    Explanations

    programmers, books, and tutorials

    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
    ACC
    -0.07
    _sched
    -0.06
    atsapp
    -0.06
     Estimates
    -0.06
    æݨ广
    -0.06
    çŃ·åŃIJ
    -0.06
     mainland
    -0.06
     abroad
    -0.06
     favourable
    -0.06
    å£
    -0.06
    POSITIVE LOGITS
     chapter
    0.10
     chapters
    0.09
     tutorial
    0.09
    æľ¬ç«ł
    0.09
    ä¸Ĭä¸Ģç«ł
    0.09
    çļĦé«ĺ级
    0.08
     tutorials
    0.08
    å®ŀæĪĺ
    0.08
     Chapter
    0.08
    æľ¬æĽ¸
    0.08
    Activations Density 0.515%

    No Known Activations