© 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. 48870
    Prev
    Next
    INDEX
    Explanations

    numbers and roman numerals

    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
    à¸ŀั
    -0.07
    ä¸įåħī
    -0.07
    cpy
    -0.06
    nese
    -0.06
    orgen
    -0.06
    å©Ĩ
    -0.06
    ׳ק
    -0.06
    /english
    -0.06
    ׼ף
    -0.06
    äh
    -0.06
    POSITIVE LOGITS
     recent
    0.07
    層çļĦ
    0.07
    (?)
    0.07
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    0.07
    åı¤å±ĭ
    0.07
    å¸ĮæľĽå¯¹æĤ¨
    0.07
    ámara
    0.06
    erien
    0.06
     annex
    0.06
    对äºĨ
    0.06
    Activations Density 0.218%

    No Known Activations