© 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. 4802
    Prev
    Next
    INDEX
    Explanations

    answers, comments, and definitions

    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
    å¸Ĥæĸ°
    -0.08
    -sama
    -0.07
    áĥĶáĥijáĥĺáĥĹ
    -0.07
    èĭ¥å¹²
    -0.07
    ServerError
    -0.07
    erst
    -0.07
    μβ
    -0.07
    —even
    -0.07
    寥寥
    -0.06
    >*</
    -0.06
    POSITIVE LOGITS
    uhl
    0.07
    à¸Ķà¹īวยà¸ģัà¸Ļ
    0.07
    à¹Ģà¸Ľà¸£
    0.07
    รวà¸Ķ
    0.07
    åŃĺçļĦ
    0.07
    ìĿĮ
    0.07
     chacune
    0.06
     cada
    0.06
    AYS
    0.06
    以ä¸Ĭ
    0.06
    Activations Density 0.123%

    No Known Activations