© 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. 14017
    Prev
    Next
    INDEX
    Explanations

    say "主题"

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

    No Comments

    Negative Logits
     testers
    -21.50
    :test
    -18.75
    [Test
    -18.63
    テスト
    -18.00
    ��
    -18.00
    	tests
    -18.00
    apot
    -17.63
    )test
    -17.38
     tests
    -17.13
     teste
    -17.00
    POSITIVE LOGITS
    主题
    18.88
    报
    18.25
    论坛
    17.88
    议题
    16.50
    报告
    16.50
    Forum
    16.50
    活动
    16.25
    话题
    16.00
    Topics
    15.94
    嘉宾
    15.94
    Activations Density 0.588%

    No Known Activations