© 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. 9227
    Prev
    Next
    INDEX
    Explanations

    each

    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¯į亲çļĦ
    -0.08
     quãng
    -0.08
    inton
    -0.08
    vg
    -0.07
    æĻĸ
    -0.07
    大åįĬ
    -0.07
    виа
    -0.07
    cab
    -0.07
    ç²±
    -0.07
    cul
    -0.07
    POSITIVE LOGITS
    æĺ¯æ¯ı个
    0.09
    åľ¨æ¯ı个
    0.09
     each
    0.09
    对åIJĦ
    0.09
    æ¯ı个
    0.08
     EACH
    0.08
     Each
    0.08
    each
    0.08
    æ¯ıæĪ·
    0.08
    à¹ĥà¸Ļà¹ģà¸ķà¹Īละ
    0.08
    Activations Density 0.083%

    No Known Activations