© 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. 27733
    Prev
    Next
    INDEX
    Explanations

    varying between individuals

    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
    Timeline
    -0.08
    idian
    -0.07
    ÙĪÙİ
    -0.07
    arning
    -0.07
    è¡£é£Ł
    -0.07
    IZZ
    -0.07
    WOR
    -0.07
    à¸Ĺัà¹īà¸ĩà¸Ħูà¹Ī
    -0.07
    ä¸įéĹ´æĸŃ
    -0.07
     Timeline
    -0.07
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ
    0.13
     variation
    0.13
     different
    0.12
     variations
    0.12
    æľīä¸įåIJĮçļĦ
    0.11
    different
    0.11
    æĺ¯ä¸įåIJĮçļĦ
    0.11
    éĢīæĭ©ä¸įåIJĮçļĦ
    0.11
     Variation
    0.10
    Different
    0.10
    Activations Density 0.136%

    No Known Activations