© 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. 952
    Prev
    Next
    INDEX
    Explanations

    say ancient Chinese rulers

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

    No Comments

    Negative Logits
    红茶
    -24.63
     Cocoa
    -22.75
    茉
    -21.50
    白糖
    -21.38
    蔗
    -20.75
    阿根廷
    -20.63
    フランス
    -19.38
    草莓
    -19.25
    樟
    -19.13
    奶油
    -19.00
    POSITIVE LOGITS
     Qin
    21.38
    羿
    20.63
    稷
    20.63
    禹
    20.38
    尧
    19.75
    濮
    19.50
    嬴
    19.50
    鲧
    19.13
    羲
    19.00
    炎
    18.88
    Activations Density 0.204%

    No Known Activations