© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1829
    Prev
    Next
    INDEX
    Explanations

    say "wave"

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

    No Comments

    Negative Logits
    体育
    -38.75
     athletic
    -24.75
     athletes
    -24.00
     sports
    -23.50
     athlete
    -23.38
     sport
    -23.25
    SPORT
    -23.00
    athlete
    -22.25
     athletics
    -21.75
     Sport
    -21.63
    POSITIVE LOGITS
    波
    17.38
     sóng
    17.00
     Ca
    17.00
    Ca
    16.88
    樱花
    16.25
    wave
    16.25
     wave
    16.25
    /wiki
    16.00
     waves
    15.31
     Wave
    15.31
    Activations Density 0.054%

    No Known Activations