© 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. 2756
    Prev
    Next
    INDEX
    Explanations

    say "par" words

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

    No Comments

    Negative Logits
    odia
    -14.94
    老头
    -14.81
    ASTER
    -14.56
    etically
    -14.38
    .untracked
    -13.81
    atham
    -13.75
    creen
    -13.63
    ummer
    -13.56
    手掌
    -13.50
    宝宝
    -13.25
    POSITIVE LOGITS
     par
    95.50
     Par
    88.00
    Par
    84.00
    par
    83.50
    (par
    76.50
    -par
    75.00
    _par
    74.50
    .par
    73.00
    .Par
    60.00
     PAR
    59.75
    Activations Density 0.356%

    No Known Activations