© 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. 1754
    Prev
    Next
    INDEX
    Explanations

    socket

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

    No Comments

    Negative Logits
     socket
    -33.25
    	socket
    -32.25
    Socket
    -30.75
    socket
    -30.75
     sockets
    -29.75
    _socket
    -29.13
     Socket
    -28.88
    _SOCKET
    -28.75
    sockets
    -27.50
    	sock
    -26.13
    POSITIVE LOGITS
    lyph
    18.50
    Digits
    17.25
    文学
    17.00
     ML
    16.88
    文學
    16.75
    神经
    16.38
    文字
    16.00
    _digits
    15.63
     digits
    15.63
     Csv
    15.25
    Activations Density 0.079%

    No Known Activations