© 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. 1139
    Prev
    Next
    INDEX
    Explanations

    [轮] => [轮]

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

    No Comments

    Negative Logits
    -wheel
    -22.50
     wheel
    -22.38
    wheel
    -21.63
    齿轮
    -21.38
     cir
    -20.75
     Arabs
    -20.75
     Arab
    -20.25
     Wheels
    -19.25
    HEEL
    -19.25
    ARTH
    -19.00
    POSITIVE LOGITS
    美军
    21.00
    闽
    17.63
    语言
    17.13
    美
    16.88
     beauty
    16.25
     Beauty
    15.88
    consume
    15.31
    消费品
    15.19
    拉丁
    15.00
    consum
    14.63
    Activations Density 0.048%

    No Known Activations