© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14216
    Prev
    Next
    INDEX
    Explanations

    say "template"

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

    No Comments

    Negative Logits
     program
    -39.00
     programs
    -36.25
    program
    -36.00
     Program
    -36.00
    Program
    -36.00
    _program
    -35.00
    programs
    -34.50
     PROGRAM
    -34.25
    (program
    -34.25
     Programs
    -34.00
    POSITIVE LOGITS
    模板
    19.25
     template
    19.00
     templates
    18.00
     Template
    17.63
     TEMPLATE
    17.00
    Template
    16.88
    (template
    16.50
     insertion
    16.00
     templ
    15.56
    $template
    15.44
    Activations Density 0.973%

    No Known Activations