© 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. 59958
    Prev
    Next
    INDEX
    Explanations

    spreadsheet, loop, matrix, hrs

    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
    éļıä¹ĭ
    -0.08
    éĽªä¸Ń
    -0.07
    ÃŃze
    -0.07
    peen
    -0.07
    èıł
    -0.07
     either
    -0.06
    vido
    -0.06
     trùng
    -0.06
    åħ¬åı¸åľ¨
    -0.06
    è¯ĬæĸŃåıĬ
    -0.06
    POSITIVE LOGITS
    èĢĮéĿŀ
    0.11
    èĢĮä¸įæĺ¯
    0.11
     rather
    0.10
    )':
    0.09
    çļĦ人æĿ¥è¯´
    0.09
     plutôt
    0.09
     instead
    0.09
    instead
    0.08
    )":
    0.08
    rather
    0.08
    Activations Density 0.029%

    No Known Activations