© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1441
    Prev
    Next
    INDEX
    Explanations

    [弹] => [尽]

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

    No Comments

    Negative Logits
     elastic
    -27.50
    弹
    -27.13
     Elastic
    -25.63
    彈
    -25.63
    弹性
    -24.25
    elastic
    -22.25
     elasticity
    -21.38
    EL
    -21.00
    elts
    -20.88
     EL
    -20.63
    POSITIVE LOGITS
    法院
    21.25
     Court
    19.25
     QtCore
    18.50
     court
    18.13
    Court
    17.75
     QImage
    17.25
     Qt
    16.88
    /qt
    16.50
    court
    16.38
    茶
    16.00
    Activations Density 0.075%

    No Known Activations