© 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. 3262
    Prev
    Next
    INDEX
    Explanations

    say figure

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     treatment
    -18.75
    estate
    -17.00
    unken
    -15.50
    OfString
    -15.44
    apia
    -15.38
     Treatment
    -14.75
    .readString
    -14.44
     Komm
    -14.44
    reatment
    -14.31
    ologne
    -14.31
    POSITIVE LOGITS
     figure
    70.50
     Figure
    69.50
    Figure
    64.50
    figure
    61.50
    _figure
    53.00
     figures
    51.50
     Figures
    50.00
    图
    48.75
    -figure
    46.75
    .figure
    43.50
    Activations Density 0.227%

    No Known Activations