© 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. 54931
    Prev
    Next
    INDEX
    Explanations

    job titles and roles

    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
    æĿĥå¨ģçļĦ
    -0.08
    ÑĪнÑĭе
    -0.08
    以åħįéĢłæĪIJ
    -0.08
    ä½ľä¸º
    -0.08
    ä¸įæĶ¾
    -0.07
    inator
    -0.07
    ÑĪнÑĭÑħ
    -0.07
    adian
    -0.07
    aul
    -0.07
    adeiras
    -0.07
    POSITIVE LOGITS
    åħ¼
    0.09
    åħ¼æĢ»ç»ıçIJĨ
    0.08
    óta
    0.07
     specializing
    0.06
    ä¸ĢèģĮ
    0.06
    人äºĭ
    0.06
    nyi
    0.06
    çݺ
    0.06
     Brot
    0.06
    级
    0.06
    Activations Density 0.327%

    No Known Activations