© 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. 7497
    Prev
    Next
    INDEX
    Explanations

    invention and function

    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
    ÏĥÏĩ
    -0.09
    å·¡è§Ĩåijĺ
    -0.07
    Ñģпи
    -0.07
    éĶĻ
    -0.07
    人åĿĩåı¯
    -0.07
    éĮ¯
    -0.07
    à¸ľà¸´à¸Ķ
    -0.07
    onto
    -0.07
    æĴŀ
    -0.06
    ForResult
    -0.06
    POSITIVE LOGITS
    èģļ
    0.08
    udd
    0.07
    éĽĨ
    0.07
     tụ
    0.07
    åIJĪ
    0.07
    icar
    0.07
    ä¹ŀ
    0.07
     aggreg
    0.06
    离å©ļ
    0.06
    èģļåIJĪ
    0.06
    Activations Density 0.008%

    No Known Activations