© 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. 14043
    Prev
    Next
    INDEX
    Explanations

    say writing

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

    No Comments

    Negative Logits
    公开招聘
    -17.13
    xDE
    -16.38
    -area
    -15.50
    _estimator
    -14.44
    _mag
    -14.19
    �
    -14.19
    xCD
    -14.06
     runway
    -13.94
    的地图
    -13.88
    面积约
    -13.63
    POSITIVE LOGITS
    写
    25.00
    扩展
    24.25
     writing
    24.13
     Writing
    23.13
    写作
    22.00
     write
    21.88
    寫
    21.88
    解析
    21.75
    扩
    21.75
    写出
    21.50
    Activations Density 1.100%

    No Known Activations