© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1195
    Prev
    Next
    INDEX
    Explanations

    say "smoke"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    床
    -22.13
     bed
    -18.38
     BED
    -17.88
    宫廷
    -16.25
    bed
    -16.13
    床上
    -16.13
    窗
    -16.00
    院
    -16.00
    python
    -15.69
    .edu
    -15.25
    POSITIVE LOGITS
    抽烟
    21.50
    吸烟
    20.88
     smoke
    20.00
     scripts
    19.38
     Smith
    19.38
    -Smith
    19.38
    (sm
    19.25
     Smoke
    19.00
    烟草
    18.88
    $log
    18.75
    Activations Density 0.219%

    No Known Activations