© 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. 52219
    Prev
    Next
    INDEX
    Explanations

    sync, cache, backup, false

    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
    urier
    -0.08
    CONDITION
    -0.08
    é£ŀæĿ¥
    -0.08
    足
    -0.07
    å²ģå²ģ
    -0.07
    atica
    -0.07
    letic
    -0.07
    说起æĿ¥
    -0.07
    à¬Ĩ
    -0.06
    piar
    -0.06
    POSITIVE LOGITS
    ertext
    0.07
    -align
    0.07
    born
    0.06
    они
    0.06
    ocha
    0.06
    essim
    0.06
    less
    0.06
    å¼łå°ı
    0.06
    æĿı
    0.06
    rio
    0.06
    Activations Density 0.001%

    No Known Activations