© 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. 19807
    Prev
    Next
    INDEX
    Explanations

    units digit of numbers

    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
    _digest
    -0.07
    HORT
    -0.07
    hort
    -0.07
    ÙģÙĪ
    -0.07
    èĩªæĭħ
    -0.07
    onti
    -0.07
    èij©
    -0.07
    .Encode
    -0.06
    ont
    -0.06
    æĺ¯ä»Ģä¹Īæł·
    -0.06
    POSITIVE LOGITS
    ç§ĴæĿĢ
    0.07
    еÑģÑĤво
    0.07
    رÙĪس
    0.07
    åįģä¸ī
    0.07
    Spo
    0.07
    æįIJ
    0.07
     Eisen
    0.07
    êng
    0.07
     Spo
    0.07
    razi
    0.06
    Activations Density 0.002%

    No Known Activations