© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13921
    Prev
    Next
    INDEX
    Explanations

    [劳] => [而]

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

    No Comments

    Negative Logits
     transfer
    -20.38
    .transfer
    -20.25
    transfer
    -20.25
     transfers
    -19.88
    -trans
    -19.75
    传播
    -19.75
     transferred
    -19.63
     transferring
    -19.38
     TRANS
    -18.88
    实施
    -18.38
    POSITIVE LOGITS
    定义
    21.00
     definition
    20.38
    编
    19.88
    组合
    19.38
    definition
    19.13
    _definition
    18.88
     combination
    18.75
    序列
    18.75
    ndef
    18.75
    Comb
    18.63
    Activations Density 0.918%

    No Known Activations