© 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. 14041
    Prev
    Next
    INDEX
    Explanations

    say project

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

    No Comments

    Negative Logits
    药店
    -16.38
    お店
    -15.81
     SetProperty
    -15.06
    	connection
    -14.94
     fittings
    -14.88
    裨
    -14.88
     kinky
    -14.81
     countert
    -14.81
     gutter
    -14.75
     Selling
    -14.75
    POSITIVE LOGITS
    项目
    20.88
    运行
    20.38
    测试
    20.00
    参数
    19.63
    运
    18.50
    项
    18.25
    项目的
    17.88
    研制
    17.88
    任务
    17.63
    试验
    17.63
    Activations Density 0.295%

    No Known Activations