© 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. 2656
    Prev
    Next
    INDEX
    Explanations

    say 丝

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

    No Comments

    Negative Logits
    dem
    -18.75
     dem
    -18.50
     rem
    -18.00
     Rem
    -17.25
    -dem
    -16.63
     Dem
    -15.75
    Dem
    -15.69
     denom
    -15.56
    嘎
    -15.25
    den
    -15.06
    POSITIVE LOGITS
    丝
    83.50
    絲
    71.00
     Ser
    53.50
     ser
    50.25
    Ser
    48.50
     Serial
    46.50
     fil
    46.50
    Serial
    45.25
    (serial
    44.75
     serial
    44.00
    Activations Density 0.044%

    No Known Activations