© 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. 1014
    Prev
    Next
    INDEX
    Explanations

    Chinese imperial exams

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

    No Comments

    Negative Logits
    经营者
    -19.25
     OS
    -18.38
    安检
    -18.13
    奥斯
    -18.13
    冰淇淋
    -18.00
    洛杉矶
    -18.00
    葡萄酒
    -18.00
    (OS
    -17.75
    项目经理
    -17.63
    滑雪
    -17.50
    POSITIVE LOGITS
     Zhu
    20.88
    莆田
    18.50
     Jiang
    18.13
    塾
    17.13
     Zhang
    16.75
    柳州
    16.38
    扬州
    16.00
    乾隆
    15.94
    梅州
    15.63
    嵇
    15.56
    Activations Density 0.145%

    No Known Activations