© 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. 14035
    Prev
    Next
    INDEX
    Explanations

    say "properties"

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

    No Comments

    Negative Logits
     mailed
    -17.13
    コース
    -16.88
    電話
    -16.88
     cunt
    -16.63
    	dev
    -15.88
     flare
    -15.69
     condi
    -15.69
    カメラ
    -15.63
     curve
    -15.44
     handset
    -15.31
    POSITIVE LOGITS
    顺序
    20.00
    选择
    19.50
    具体
    19.13
    结构
    19.00
    外
    18.75
    动态
    18.63
    供
    18.13
    机
    18.13
    信息
    18.00
    总
    17.75
    Activations Density 0.362%

    No Known Activations