© 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. 55458
    Prev
    Next
    INDEX
    Explanations

    months, Ave, processes

    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
     inc
    -0.07
    ä¸įå¸ĮæľĽ
    -0.06
    åĵģ
    -0.06
    å¹³åĿĩæ¯ı
    -0.06
    alie
    -0.06
     kit
    -0.06
    IFT
    -0.06
     Kit
    -0.06
    ä¸ŃæĸĩåIJį
    -0.06
    Kit
    -0.06
    POSITIVE LOGITS
    鸳
    0.09
    ingk
    0.08
    èĢĮçŁ¥
    0.07
    åħµåĽ¢
    0.07
    çijŀæĭī
    0.07
    #
    0.07
    ä¹ĭé£İ
    0.07
    çais
    0.07
    婧
    0.07
    æĺ¥æļĸ
    0.07
    Activations Density 0.001%

    No Known Activations