© 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. 2110
    Prev
    Next
    INDEX
    Explanations

    say "vis" words

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

    No Comments

    Negative Logits
    asher
    -16.13
     дело
    -15.63
    安东
    -15.63
     poles
    -14.88
     Ivory
    -14.50
     Jerome
    -14.50
    olon
    -14.50
    uctions
    -14.13
     incumb
    -13.81
    水上
    -13.81
    POSITIVE LOGITS
    (vis
    77.00
     Vis
    75.00
     vis
    75.00
    Vis
    73.50
    .vis
    71.00
    vis
    71.00
    -vis
    66.50
    _vis
    60.00
     visit
    55.50
     visited
    55.00
    Activations Density 0.061%

    No Known Activations