© 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. 14028
    Prev
    Next
    INDEX
    Explanations

    say "load"

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

    No Comments

    Negative Logits
     connection
    -49.50
    连接
    -47.25
     connections
    -44.00
    connection
    -43.50
     Connection
    -42.50
     connecting
    -41.75
     connect
    -41.00
    _connection
    -40.25
     connects
    -40.25
    connections
    -39.50
    POSITIVE LOGITS
     loads
    20.13
    负载
    20.00
    _load
    20.00
    _Load
    19.88
     load
    19.75
    Load
    19.38
     Load
    19.00
    load
    18.00
     Loads
    17.88
    加载
    17.75
    Activations Density 0.902%

    No Known Activations