© 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. 1878
    Prev
    Next
    INDEX
    Explanations

    Russian, Latvian, and other Slavic 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
    çļĦ
    -0.15
    ìĿĺ
    -0.12
    çļĦä¸įåIJĮ
    -0.10
    ãģ®
    -0.10
    çļĦåIJĮæŶ
    -0.09
    çļĦäºĨ
    -0.09
    çļĦæĪij
    -0.08
    çļĦè§Ĵ度
    -0.08
    çļĦåIJĦç§į
    -0.08
    çļĦåİĨåı²
    -0.08
    POSITIVE LOGITS
    ÙĮ
    0.11
    ÙĮÙij
    0.11
    ÑĬÑĤ
    0.11
    ÙİØ©ÙĮ
    0.10
    æĿ¥çļĦæŶåĢĻ
    0.09
    人æĪĸ
    0.09
    ÙİØ©Ùı
    0.08
    ؤÙĩ
    0.08
    ниÑıÑĤ
    0.08
    orent
    0.08
    Activations Density 0.065%

    No Known Activations