© 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. 39016
    Prev
    Next
    INDEX
    Explanations

    partial fraction

    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
    -org
    -0.08
    [++
    -0.08
    arge
    -0.07
    ÙĬز
    -0.07
    ilea
    -0.07
    urai
    -0.07
    .virtual
    -0.07
     Sue
    -0.07
    apus
    -0.07
    ake
    -0.07
    POSITIVE LOGITS
    åįł
    0.15
    åįłæĢ»
    0.13
     partial
    0.13
     fraction
    0.13
    约åįł
    0.12
    æİ¥è¿ij
    0.12
    partial
    0.11
    Partial
    0.11
    åįłæ¯Ķ
    0.11
    _fraction
    0.11
    Activations Density 0.172%

    No Known Activations