© 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. 61306
    Prev
    Next
    INDEX
    Explanations

    numbers and numerical expressions

    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
    ropp
    -0.06
    à¸ļัà¸ķิ
    -0.06
    immer
    -0.06
    ajs
    -0.06
     Teddy
    -0.06
    STE
    -0.06
    AVING
    -0.06
    è¶Ĭéĩİ车
    -0.06
    OMATIC
    -0.06
     Personally
    -0.06
    POSITIVE LOGITS
    ä¸įæĦ§æĺ¯
    0.07
    teenth
    0.07
    æĿ¥æºIJäºİç½ij绾
    0.07
    å·¥ç¨ĭçŃī
    0.07
    orni
    0.07
    åįİé¾Ļ
    0.07
    ettino
    0.07
    ÄĹja
    0.07
    thew
    0.07
     nữa
    0.06
    Activations Density 0.004%

    No Known Activations