© 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. 1118
    Prev
    Next
    INDEX
    Explanations

    say "socket"

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

    No Comments

    Negative Logits
    铋
    -18.75
    皇宫
    -18.50
    α
    -17.75
    皇子
    -17.63
    ali
    -17.50
    神话
    -17.50
    佛陀
    -17.13
    锚
    -16.50
     innovate
    -16.25
     Gotham
    -16.13
    POSITIVE LOGITS
    Socket
    19.00
     socket
    18.38
     Lamb
    18.13
    _socket
    17.63
    .sock
    17.13
    菜
    17.13
    sheet
    16.88
    (socket
    16.88
    WS
    16.75
     Lindsay
    16.75
    Activations Density 0.372%

    No Known Activations