© 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. 2968
    Prev
    Next
    INDEX
    Explanations

    say "配" words

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

    No Comments

    Negative Logits
    _RAD
    -18.50
    帝
    -17.88
     Fort
    -17.50
    ерт
    -17.25
    рад
    -16.75
    fort
    -16.50
     Josh
    -16.38
    bers
    -16.38
     Bers
    -16.38
    idx
    -16.25
    POSITIVE LOGITS
    配
    71.50
    配上
    37.25
    ��
    35.25
    配置
    25.25
    配有
    23.00
    配料
    22.75
     par
    22.75
     Par
    22.50
     config
    22.00
     Config
    21.88
    Activations Density 0.085%

    No Known Activations