© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16314
    Prev
    Next
    INDEX
    Explanations

    say watercraft terms

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

    No Comments

    Negative Logits
    珠
    -31.50
     Monk
    -26.25
     Quincy
    -25.13
    σ
    -24.38
    雀
    -24.25
    sigma
    -24.00
    红豆
    -23.75
    珍珠
    -23.38
    (sigma
    -23.25
    癞
    -22.50
    POSITIVE LOGITS
    IRO
    25.00
    巡航
    24.13
     curl
    23.00
    桨
    22.88
     Mosul
    22.75
    潘
    22.63
    棹
    22.00
    胰
    21.88
    curl
    21.63
     Raf
    21.50
    Activations Density 6.984%

    No Known Activations