© 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. 25839
    Prev
    Next
    INDEX
    Explanations

    Japanese given names, professions, places

    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
     tost
    -0.07
    ãĥ³ãĥĹ
    -0.07
    æīĢ欲
    -0.07
    æĩĪ
    -0.07
    etest
    -0.07
    .nodeType
    -0.07
    uro
    -0.06
    Disposed
    -0.06
    人æĥħ
    -0.06
    indr
    -0.06
    POSITIVE LOGITS
    走好
    0.08
    WISE
    0.08
    omat
    0.07
    amat
    0.07
     Bath
    0.07
    次éĺħ读
    0.07
    åĬŀäºĨ
    0.07
    ativement
    0.07
    æĪijåIJĥ
    0.06
    angkan
    0.06
    Activations Density 0.132%

    No Known Activations