© 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. 1963
    Prev
    Next
    INDEX
    Explanations

    [smoke] => [dust]

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

    No Comments

    Negative Logits
    烟
    -57.75
     smoke
    -56.00
     Smoke
    -50.50
    煙
    -49.25
     smoking
    -45.25
    Smoke
    -45.25
     Smoking
    -44.25
    吸烟
    -43.75
     smoker
    -43.50
     smoked
    -42.25
    POSITIVE LOGITS
     Christian
    17.25
    法律
    15.88
    基督教
    15.50
    β
    15.38
    Legal
    15.31
    beta
    14.94
    (header
    14.75
    歌词
    14.69
     header
    14.19
     β
    14.19
    Activations Density 0.048%

    No Known Activations