© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 584
    Prev
    Next
    INDEX
    Explanations

    say "Confucian concepts"

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

    No Comments

    Negative Logits
    鞍
    -23.50
    Chocolate
    -22.25
    镍
    -20.88
     chocolate
    -20.88
     chocol
    -20.88
    巧克力
    -20.38
    车队
    -20.00
    猞
    -19.88
    切尔西
    -19.38
    饼干
    -19.13
    POSITIVE LOGITS
    儒家
    32.50
    孔子
    28.25
     Zhou
    26.88
     Yuan
    25.50
     Chinese
    25.13
    儒
    24.88
     Zhu
    24.50
     Xia
    24.25
     Taiwanese
    24.25
     Jiang
    23.88
    Activations Density 0.297%

    No Known Activations