© 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. 7722
    Prev
    Next
    INDEX
    Explanations

    foreign origin words

    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
     what
    -0.07
    æĢ§åıĬ
    -0.07
    most
    -0.06
    æĢ§çĸ¾çĹħ
    -0.06
    çľī
    -0.06
    ç³»
    -0.06
    ÑĢеди
    -0.06
    åŀĭ
    -0.06
    æĢ§çļĦ
    -0.06
    what
    -0.06
    POSITIVE LOGITS
    ãģ¨åij¼ãģ°ãĤĮãĤĭ
    0.09
    /--
    0.08
    egno
    0.08
    ุà¹Īม
    0.08
    Ö¼
    0.08
    esis
    0.07
    ä¸įé½IJ
    0.07
    —the
    0.07
    hati
    0.07
    CLS
    0.07
    Activations Density 0.372%

    No Known Activations