© 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. 11523
    Prev
    Next
    INDEX
    Explanations

    urticaria, upset, value, variant, air, class, sensory, checkpoint, header

    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
    ymp
    -0.07
    ä¸į移
    -0.07
    yms
    -0.07
    åįļ大
    -0.07
     bound
    -0.06
    úst
    -0.06
    nud
    -0.06
    à¸Ńาà¸Ķ
    -0.06
    ÑĤива
    -0.06
    åŀ¢
    -0.06
    POSITIVE LOGITS
     заÑĤо
    0.09
    ihar
    0.08
    ordia
    0.08
    avan
    0.07
    è¿Ļæīį
    0.07
     sÃŃ
    0.07
    åĴĮåIJĮåѦ
    0.07
     contraire
    0.07
    æ¸ħæ¥ļ
    0.07
    çļĦåIJĮåѦ
    0.07
    Activations Density 0.242%

    No Known Activations