© 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. 2784
    Prev
    Next
    INDEX
    Explanations

    say "per" words

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

    No Comments

    Negative Logits
    条
    -20.88
    條
    -20.13
     strip
    -17.13
    汤
    -16.88
    ialect
    -16.63
    湯
    -16.38
     Settlement
    -15.94
     pea
    -15.75
    tery
    -15.31
    TER
    -15.19
    POSITIVE LOGITS
     Per
    60.25
    Per
    59.75
    (per
    54.75
     perm
    54.00
    perm
    52.50
    per
    52.50
    -per
    50.75
    Perm
    49.00
     per
    48.25
     percept
    47.50
    Activations Density 0.175%

    No Known Activations