© 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. 21682
    Prev
    Next
    INDEX
    Explanations

    named after

    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
    æ´ªèįĴ
    -0.09
    !!:
    -0.08
    orsi
    -0.08
    ongi
    -0.08
    unga
    -0.08
    amburg
    -0.08
    èIJ¨æĸ¯
    -0.08
    ahari
    -0.08
     McKay
    -0.08
    onger
    -0.08
    POSITIVE LOGITS
    èĢĮå¾ĹåIJį
    0.14
     appunto
    0.09
    æķħåIJį
    0.09
     allegedly
    0.07
    å¼ķçĶ³
    0.07
    à¸ķà¸Ńà¸Ļ
    0.07
     ÑıкобÑĭ
    0.07
    æķħ
    0.07
    æķħæѤ
    0.06
    æīĢ以大家
    0.06
    Activations Density 0.365%

    No Known Activations