© 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. 2639
    Prev
    Next
    INDEX
    Explanations

    say "million"

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

    No Comments

    Negative Logits
    _ctx
    -19.63
    ctx
    -18.38
     recurs
    -18.13
    dirs
    -18.00
    .ctx
    -17.75
     ctx
    -17.38
    dir
    -17.38
    Ctx
    -17.13
    _cur
    -16.88
    VAR
    -16.63
    POSITIVE LOGITS
     million
    59.00
    million
    53.00
    万
    51.75
     Million
    50.50
    Mill
    49.50
     thousand
    46.75
    千
    46.75
    -million
    46.00
    萬
    45.75
    百万
    45.50
    Activations Density 0.143%

    No Known Activations