© 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. 44566
    Prev
    Next
    INDEX
    Explanations

    javascript variable declaration

    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
    浦路
    -0.08
    æĢ¥
    -0.07
    endregion
    -0.07
    cq
    -0.07
    éĤ¯éĥ¸
    -0.07
    apus
    -0.07
    .mozilla
    -0.07
    ITH
    -0.07
    ith
    -0.07
    ooth
    -0.07
    POSITIVE LOGITS
     div
    0.07
    åĽ½éĻħå¸Ĥåľº
    0.07
    ayah
    0.07
    аÑĢÑĤ
    0.07
     come
    0.06
    æĬĵåĪ°
    0.06
     coming
    0.06
    ارÙģ
    0.06
    ales
    0.06
    andos
    0.06
    Activations Density 0.222%

    No Known Activations