© 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. 1324
    Prev
    Next
    INDEX
    Explanations

    do not say Arab

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

    No Comments

    Negative Logits
     Arabs
    -38.50
     Arab
    -38.50
    阿拉伯
    -37.50
     Arabic
    -37.00
     Muslim
    -33.75
    伊斯兰
    -33.50
     Islamic
    -32.50
     Arabia
    -30.63
     muslim
    -30.00
     arab
    -29.75
    POSITIVE LOGITS
    酒
    18.50
     Wine
    15.13
    酒业
    14.88
    酿酒
    14.81
    inson
    14.69
    KR
    14.13
    USIC
    14.06
    ян
    13.88
    濟
    13.81
    matrix
    13.69
    Activations Density 0.175%

    No Known Activations