© 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. 1877
    Prev
    Next
    INDEX
    Explanations

    say smoke

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

    No Comments

    Negative Logits
    货币
    -26.13
     currency
    -24.88
     currencies
    -23.13
    _currency
    -22.75
    currency
    -22.13
    URRENCY
    -20.50
    .currency
    -19.13
     Currency
    -19.00
    美元
    -19.00
    Currency
    -18.88
    POSITIVE LOGITS
    抽烟
    18.63
    oil
    17.50
     smoke
    17.25
    烟
    17.25
    车
    16.38
    煙
    15.50
     SM
    15.38
     Smoking
    15.25
     smoking
    15.06
     Smoke
    14.75
    Activations Density 0.088%

    No Known Activations