© 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. 1366
    Prev
    Next
    INDEX
    Explanations

    [design] => [syntax]

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

    No Comments

    Negative Logits
    设计
    -59.75
     design
    -57.75
     Design
    -54.75
    Design
    -51.75
     designs
    -51.25
    的设计
    -51.00
    design
    -50.50
     DESIGN
    -48.50
    _design
    -48.00
     designing
    -47.00
    POSITIVE LOGITS
    语法
    16.50
    CUDA
    16.25
    urg
    16.13
     NGX
    15.94
    英镑
    15.63
    Grammar
    15.31
    彘
    15.31
    _CUDA
    15.31
     syntax
    15.06
    egl
    14.81
    Activations Density 0.306%

    No Known Activations