© 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. 1043
    Prev
    Next
    INDEX
    Explanations

    say magnet

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    希腊
    -53.50
     Greek
    -52.25
    Greek
    -48.50
     Greeks
    -47.00
     Greece
    -43.75
     json
    -34.50
     JSON
    -34.25
    JSON
    -34.00
    -json
    -33.75
    json
    -33.25
    POSITIVE LOGITS
    磁
    19.50
     magnet
    19.50
    稀土
    19.38
     magnets
    18.13
    铷
    17.38
     Magnet
    16.50
     magnetic
    16.25
    唱歌
    15.63
     Dayton
    15.38
     Bedford
    15.13
    Activations Density 0.103%

    No Known Activations