© 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. 2129
    Prev
    Next
    INDEX
    Explanations

    say "per"

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

    No Comments

    Negative Logits
    量化
    -16.13
    Caps
    -15.94
    RESH
    -15.94
     Capitals
    -15.75
    char
    -15.25
     Antoine
    -14.75
     tử
    -14.38
     Quant
    -14.25
    uent
    -14.06
    ,char
    -14.06
    POSITIVE LOGITS
     per
    74.00
    Per
    70.00
     Per
    69.50
    (per
    68.50
    per
    68.00
    _per
    63.50
    -per
    61.75
    .per
    60.25
    _PER
    55.75
    /per
    54.50
    Activations Density 0.118%

    No Known Activations