© 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. 14262
    Prev
    Next
    INDEX
    Explanations

    say "regulation"

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

    No Comments

    Negative Logits
    辗
    -16.13
    在游戏中
    -15.94
    游戏角色
    -15.63
    囤
    -14.94
     glyphs
    -14.88
     seeds
    -14.56
    象征
    -14.56
     drawable
    -14.50
    驮
    -14.44
     forecast
    -14.38
    POSITIVE LOGITS
    规定的
    26.13
    规定
    24.25
    規定
    23.25
     specification
    22.75
     Specifications
    22.25
     regulation
    22.00
     Specification
    21.38
    Specifications
    20.75
    的规定
    20.50
     regulations
    20.38
    Activations Density 0.563%

    No Known Activations