© 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. 1878
    Prev
    Next
    INDEX
    Explanations

    do not say smoking

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

    No Comments

    Negative Logits
    烟
    -56.50
     smoke
    -55.00
    吸烟
    -54.75
     smoking
    -54.00
     Smoking
    -51.50
     smoker
    -51.25
    抽烟
    -49.50
     Smoke
    -48.75
     smokers
    -48.25
    煙
    -46.75
    POSITIVE LOGITS
    pdf
    18.00
    bed
    16.50
     Pdf
    16.38
    军
    16.00
     PDF
    16.00
     pdf
    16.00
    .Pixel
    15.75
    PDF
    15.38
     currency
    15.31
    _pdf
    15.19
    Activations Density 0.074%

    No Known Activations