© 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. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2738
    Prev
    Next
    INDEX
    Explanations

    say large numbers

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ctx
    -18.13
    <src
    -18.00
    src
    -17.75
    ctx
    -17.50
     SRC
    -17.25
    integral
    -15.88
    [src
    -15.88
    SRC
    -15.69
    .ctx
    -15.44
    orative
    -15.31
    POSITIVE LOGITS
    万
    96.00
    萬
    79.50
     million
    60.00
     thousand
    54.75
    千
    51.25
    多万
    50.00
    million
    49.50
    一万
    48.25
    亿
    48.25
     millions
    47.25
    Activations Density 0.147%

    No Known Activations