© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14324
    Prev
    Next
    INDEX
    Explanations

    say "trading"

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

    No Comments

    Negative Logits
     photographers
    -17.50
     foto
    -17.50
     photograph
    -17.25
     fotos
    -17.13
     фотограф
    -17.00
    摄影师
    -16.75
     Fotos
    -16.63
     Photograph
    -16.50
     photographs
    -16.25
     photographer
    -16.25
    POSITIVE LOGITS
    交易
    28.63
    交易所
    25.38
    交易中心
    24.75
     trading
    24.63
     Trading
    23.13
    买卖
    23.00
    交易平台
    23.00
    券
    22.38
    Trading
    21.75
    证券交易
    21.75
    Activations Density 0.321%

    No Known Activations