© 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. 14290
    Prev
    Next
    INDEX
    Explanations

    say "intro"

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

    No Comments

    Negative Logits
    变换
    -29.25
     transformation
    -28.63
     transform
    -27.63
     Transform
    -27.50
     Transformation
    -27.25
    Transform
    -26.75
     transformations
    -26.75
     transforming
    -26.50
    转变
    -25.88
     transformed
    -25.75
    POSITIVE LOGITS
    引入
    21.13
     intro
    17.75
    引进
    17.50
    代理
    16.63
    intro
    16.00
    Intro
    15.63
     reint
    15.31
    _intro
    14.88
    进口
    14.75
     Intro
    14.31
    Activations Density 4.266%

    No Known Activations