© 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. 27526
    Prev
    Next
    INDEX
    Explanations

    rational numbers and fractions

    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
    uppe
    -0.07
    (sequence
    -0.07
    æļ§
    -0.07
    踵
    -0.07
    .sequence
    -0.07
    ×ŀש
    -0.07
    ç´«èī²çļĦ
    -0.06
    andos
    -0.06
    лÑĤ
    -0.06
    olni
    -0.06
    POSITIVE LOGITS
    æŀģ度
    0.08
     ratios
    0.08
     numerator
    0.08
     Ratio
    0.08
    _ratio
    0.08
     ratio
    0.08
     اÙĦÙĨس
    0.07
    Ratio
    0.07
     rational
    0.07
    èijĽ
    0.07
    Activations Density 0.002%

    No Known Activations