© 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. 59865
    Prev
    Next
    INDEX
    Explanations

    graphs and growth models

    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
    icino
    -0.07
    uzz
    -0.07
    OUN
    -0.07
    eu
    -0.07
    使çĶ¨èµ·æĿ¥
    -0.07
    åŁİ乡建设
    -0.07
    eut
    -0.07
    ww
    -0.07
    æĿ·
    -0.07
    uela
    -0.06
    POSITIVE LOGITS
    代表çļĦ
    0.13
    代表
    0.12
    代表äºĨ
    0.10
     representing
    0.10
    代表çĿĢ
    0.10
     Represents
    0.09
    represent
    0.09
    åѤåĦ¿
    0.09
     represent
    0.08
     represents
    0.08
    Activations Density 0.049%

    No Known Activations