© 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. 679
    Prev
    Next
    INDEX
    Explanations

    divided by

    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
    меÑĢа
    -0.08
    견
    -0.08
    IOD
    -0.07
    人åĿĩåı¯
    -0.07
    åĽĽä¸Ń
    -0.07
    å¼łè´´
    -0.07
    ead
    -0.07
     нак
    -0.07
    mir
    -0.07
    ç¢
    -0.07
    POSITIVE LOGITS
    czyn
    0.07
    çī¹éĩĮ
    0.07
    áĥ£áĥłáĥĺ
    0.06
     by
    0.06
    etz
    0.06
    huis
    0.06
    à¦ķà§ĩ
    0.06
    uckets
    0.06
    .street
    0.06
    WithEmail
    0.06
    Activations Density 0.001%

    No Known Activations