© 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. 14053
    Prev
    Next
    INDEX
    Explanations

    say "cuda"

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

    No Comments

    Negative Logits
    ListModel
    -18.38
     Connections
    -18.00
    TextEdit
    -17.75
     connections
    -17.25
     modelling
    -17.13
    .getConnection
    -16.75
    钢琴
    -16.63
    Connection
    -16.38
     CONNECTION
    -16.13
     estable
    -16.13
    POSITIVE LOGITS
    	cuda
    20.75
     kernels
    19.50
    维度
    18.50
     Kernel
    18.50
    execute
    18.50
     kernel
    18.25
     dimension
    18.25
    /host
    18.13
     cuda
    17.50
    _dtype
    17.50
    Activations Density 0.220%

    No Known Activations