© 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. 14099
    Prev
    Next
    INDEX
    Explanations

    say money

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

    No Comments

    Negative Logits
    orta
    -20.25
    hoc
    -17.50
    ushman
    -17.38
    女生
    -17.38
    致癌
    -17.13
    肺癌
    -17.00
    -split
    -16.88
    anova
    -16.75
    伤亡
    -16.50
    HORT
    -16.38
    POSITIVE LOGITS
    货币
    31.63
    币
    27.88
     Monetary
    27.63
     monetary
    27.00
     money
    26.00
    金币
    26.00
     Money
    25.75
     currency
    25.50
     Currency
    24.88
     coin
    24.38
    Activations Density 0.402%

    No Known Activations