© 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. 45154
    Prev
    Next
    INDEX
    Explanations

    voice speaking or said

    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
    åļı
    -0.08
    éĵģé¾Ļ
    -0.07
    ãģĨãģ¡ãģ«
    -0.07
    à¹Ĩ
    -0.07
    leep
    -0.07
    isht
    -0.07
    acro
    -0.07
    æĽ´å¤ļåħ³äºİ
    -0.06
    akkan
    -0.06
    issage
    -0.06
    POSITIVE LOGITS
    æĿ¥ä¸ª
    0.07
    åĪ¨
    0.07
    eron
    0.07
    Require
    0.07
    anson
    0.07
     лей
    0.07
    ÅĻej
    0.06
    ä¿Ĺè¯Ŀ说
    0.06
    ãĥ¬ãĥ¼
    0.06
    寻
    0.06
    Activations Density 0.002%

    No Known Activations