© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2902
    Prev
    Next
    INDEX
    Explanations

    numbers and 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
     Vad
    -0.08
    avor
    -0.07
    avour
    -0.07
    åıĮèĸª
    -0.07
    AVOR
    -0.07
    åIJĥçĤ¹
    -0.07
    -animate
    -0.07
    åĬĽä½ľ
    -0.07
    ç½ijåıĭä¸Ĭä¼ł
    -0.07
    åĺĪæĿĤ
    -0.07
    POSITIVE LOGITS
     alphanumeric
    0.13
     digits
    0.10
    åı·çłģ
    0.10
     numbering
    0.10
    Digits
    0.09
     hexadecimal
    0.09
    è¿Ļ个æķ°åŃĹ
    0.09
    _digits
    0.08
    æł¼å¼ı
    0.08
    _DIG
    0.08
    Activations Density 0.071%

    No Known Activations