© 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. 838
    Prev
    Next
    INDEX
    Explanations

    say design

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

    No Comments

    Negative Logits
    扫黑除恶
    -18.00
    舞蹈
    -18.00
    _students
    -17.63
    _wifi
    -17.00
    旅行社
    -16.75
    售票
    -16.63
    elda
    -16.63
     wifi
    -16.50
    睡眠
    -16.38
    .Topic
    -16.25
    POSITIVE LOGITS
     design
    19.13
     production
    18.88
    .prod
    18.38
    Production
    17.13
    的设计
    16.75
    設計
    16.75
     engines
    16.63
    发动机
    16.38
    	engine
    16.38
     designs
    16.38
    Activations Density 0.213%

    No Known Activations