© 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. 62241
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions and operators

    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
    ore
    -0.08
    _COMPILER
    -0.07
    vido
    -0.07
    smouth
    -0.07
    anches
    -0.07
    ooth
    -0.07
    shed
    -0.07
    éľ¹
    -0.07
    èį·
    -0.07
    æł¸å¿ĥçļĦ
    -0.07
    POSITIVE LOGITS
    bán
    0.08
     fraction
    0.08
    fraction
    0.08
    ellis
    0.07
    tui
    0.07
    arz
    0.07
     fractions
    0.07
    raction
    0.07
    åĶ¾
    0.07
    Fraction
    0.07
    Activations Density 0.068%

    No Known Activations