© 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. 64100
    Prev
    Next
    INDEX
    Explanations

    natural numbers and arithmetic

    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
    å¾ij
    -0.07
    å¾Ħ
    -0.07
     Gust
    -0.07
    大浪
    -0.07
     screened
    -0.06
    ä¹ĭåĬ¿
    -0.06
     eclectic
    -0.06
    æľĪåºķåīį
    -0.06
    æĦıæĥ³
    -0.06
    itic
    -0.06
    POSITIVE LOGITS
     unary
    0.08
     arithmetic
    0.08
    éIJĺ
    0.08
     integer
    0.08
     ordinal
    0.08
     infix
    0.08
     subtraction
    0.08
    åħħå®ŀ
    0.08
     numeral
    0.08
    éĴŁ
    0.08
    Activations Density 0.008%

    No Known Activations