© 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. 64293
    Prev
    Next
    INDEX
    Explanations

    traditional chinese 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
    wana
    -0.08
    æĮºèĥ¸
    -0.08
    uchu
    -0.07
    اÙģÛĮ
    -0.07
    ucci
    -0.07
    æĺ¥æ±Ł
    -0.07
    éŨåħ³
    -0.07
    ç²Ĺ
    -0.07
    енÑģи
    -0.07
    rego
    -0.07
    POSITIVE LOGITS
    ä¼łç»ŁçļĦ
    0.14
     traditionally
    0.14
    ä¼łç»Ł
    0.14
     traditional
    0.14
     tradicional
    0.12
    çļĦä¼łç»Ł
    0.12
    traditional
    0.12
    çŃīä¼łç»Ł
    0.12
    åİŁæľ¬çļĦ
    0.12
    å¾ĵæĿ¥ãģ®
    0.11
    Activations Density 0.528%

    No Known Activations