© 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. 52016
    Prev
    Next
    INDEX
    Explanations

    non-standard characters and symbols

    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
    äch
    -0.10
    zinho
    -0.09
    æģ¯
    -0.09
    åĥļ
    -0.07
    und
    -0.07
    ...**
    -0.07
    kirchen
    -0.07
    次第
    -0.07
    **”,
    -0.07
    âĢ¦),
    -0.07
    POSITIVE LOGITS
    ↵↵
    0.07
    çļĦ
    0.07
    äºĭä¸Ń
    0.06
    spo
    0.06
    ãĤĭ
    0.06
    å®£ä¼łéĥ¨
    0.06
    anut
    0.06
    ï¸ı
    0.06
    çļĦæĪij们
    0.06
    çļĦéĻĪ
    0.06
    Activations Density 0.003%

    No Known Activations