© 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. 11207
    Prev
    Next
    INDEX
    Explanations

    do you mean

    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
    对ä¸Ĭ
    -0.08
    enburg
    -0.08
    sts
    -0.08
    andr
    -0.08
    å¹´åģĩ
    -0.07
    nown
    -0.07
    eves
    -0.07
    ushman
    -0.07
    atson
    -0.07
    被称为
    -0.07
    POSITIVE LOGITS
    ä»Ģä¹Īåij¢
    0.08
    ä»Ģä¹ĪæĦıæĢĿ
    0.08
    çļĦæĦıæĢĿæĺ¯
    0.07
    æĦıæĢĿæĺ¯
    0.07
    æķ´ä¸ª
    0.07
    ť
    0.07
    çļĦæĦıæĢĿ
    0.07
    æĦıæĢĿ
    0.06
    ï¼ļ
    0.06
    éĢı
    0.06
    Activations Density 0.016%

    No Known Activations