© 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. 23913
    Prev
    Next
    INDEX
    Explanations

    control flow and code structures

    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
     thereof
    -0.07
    è¶
    -0.06
     Lastly
    -0.06
    Lastly
    -0.06
    UpdatedAt
    -0.06
     lho
    -0.06
     K
    -0.06
    наÑĤ
    -0.06
    nam
    -0.06
    borne
    -0.06
    POSITIVE LOGITS
    æķĻèĤ²æĺ¯
    0.07
    inei
    0.07
    ibat
    0.07
    ä¸įåı¯æĢķ
    0.07
    èĥĮæĻ¯çļĦ
    0.07
    身为
    0.07
    zysta
    0.07
    pret
    0.07
    æĹ¢ä¸į
    0.07
    unia
    0.07
    Activations Density 0.069%

    No Known Activations