© 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. 55592
    Prev
    Next
    INDEX
    Explanations

    summing digits

    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
    æ·ĭå·´ç»Ĩèĥŀ
    -0.07
    asel
    -0.07
     offsetof
    -0.07
    lopen
    -0.07
    oub
    -0.06
    ç»ĨåĪĻ
    -0.06
    ikum
    -0.06
    åŁĭæĢ¨
    -0.06
    _definitions
    -0.06
    åıĹåĪ°äºĨ
    -0.06
    POSITIVE LOGITS
     digits
    0.15
    digits
    0.13
    igits
    0.13
     digit
    0.13
    Digits
    0.12
    _digits
    0.12
    -digit
    0.12
    Digit
    0.11
    æķ°åŃĹ
    0.11
    decimal
    0.11
    Activations Density 0.037%

    No Known Activations