© 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. 2907
    Prev
    Next
    INDEX
    Explanations

    say "其实"

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

    No Comments

    Negative Logits
    den
    -23.00
    .den
    -22.00
    DEN
    -21.50
     Den
    -21.25
     den
    -21.00
     DEN
    -21.00
    Modifiers
    -20.00
    mods
    -19.75
    _den
    -19.50
    modifiers
    -19.25
    POSITIVE LOGITS
    其实
    25.00
    其实是
    22.00
    其實
    20.50
    其实就是
    18.63
    ​
    18.63
     replic
    18.63
     analog
    18.25
    Rep
    18.13
    ​↵↵
    17.75
    有机
    17.63
    Activations Density 0.157%

    No Known Activations