© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48465
    Prev
    Next
    INDEX
    Explanations

    Greek letters and symbols

    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
    /of
    -0.08
    /or
    -0.08
    à§įত
    -0.07
    annya
    -0.06
    -turned
    -0.06
    wards
    -0.06
    zsche
    -0.06
    ings
    -0.06
    iet
    -0.06
    umente
    -0.06
    POSITIVE LOGITS
    ï¸İ
    0.14
    ï¸ı
    0.11
    0.09
    zelfde
    0.09
    iante
    0.09
    äºĶé¢ľåħŃèī²çļĦ
    0.09
    eviÄĩ
    0.09
    åIJĦç§įåIJĦæł·
    0.09
    sburg
    0.08
    ลฯ
    0.08
    Activations Density 0.017%

    No Known Activations