© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 19284
    Prev
    Next
    INDEX
    Explanations

    medical terms and technical compositions

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸Ńèĭ±
    -0.07
     dicon
    -0.07
    ifix
    -0.07
     ÏĢÏīÏĤ
    -0.07
    æĹ¢åı¯
    -0.07
    à¹Ģละ
    -0.07
    ilup
    -0.07
    æĭ¿æįı
    -0.07
    èĻ½
    -0.07
    trup
    -0.07
    POSITIVE LOGITS
    0.18
    0.09
    æĺ¾çĿĢ
    0.09
     «
    0.08
    ìľĦíķľ
    0.07
    絶対ãģ«
    0.07
     -
    0.07
     ((((
    0.07
     («
    0.07
    å¿ħä¸įåı¯å°ij
    0.07
    Activations Density 0.036%

    No Known Activations