© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15793
    Prev
    Next
    INDEX
    Explanations

    say smoking

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

    No Comments

    Negative Logits
    .overflow
    -17.88
     Dresden
    -17.25
    用地
    -16.50
     Berry
    -16.38
    stown
    -16.13
    overflow
    -16.13
    耒
    -16.00
     Bentley
    -15.69
     berlin
    -15.31
    kop
    -15.31
    POSITIVE LOGITS
    烟
    43.00
     smokers
    41.00
     smoke
    40.00
    煙
    39.50
    吸烟
    39.00
     smoker
    38.75
    烟草
    38.00
     Smoke
    36.50
     smoking
    36.50
     nicotine
    35.25
    Activations Density 0.199%

    No Known Activations