© 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. 2334
    Prev
    Next
    INDEX
    Explanations

    say "thousand"

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

    No Comments

    Negative Logits
     Et
    -20.50
     ET
    -18.88
    .ep
    -18.13
    eta
    -17.88
    Et
    -17.75
     Mat
    -17.25
     det
    -17.00
     eta
    -16.75
     Det
    -16.63
    _ET
    -16.50
    POSITIVE LOGITS
    千
    80.50
     thousand
    59.75
     mill
    55.25
    万
    55.25
    Mill
    53.25
     million
    52.00
     Thousand
    50.50
    萬
    49.25
    mill
    49.00
     thousands
    48.75
    Activations Density 0.118%

    No Known Activations