© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15699
    Prev
    Next
    INDEX
    Explanations

    [世界] => [国际]

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

    No Comments

    Negative Logits
    UILT
    -15.44
    seud
    -15.25
    UILTIN
    -15.00
    孽
    -14.81
    PLIT
    -14.69
     separation
    -14.19
    (buff
    -13.94
     segments
    -13.94
     segment
    -13.81
    seudo
    -13.81
    POSITIVE LOGITS
    接轨
    17.00
    舞台
    17.00
    大奖
    16.50
     Capitals
    16.50
    排名
    16.38
    CommandEvent
    16.38
    品牌
    15.50
    知名品牌
    15.44
    对话
    15.44
    合作
    15.44
    Activations Density 0.248%

    No Known Activations