© 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. 990
    Prev
    Next
    INDEX
    Explanations

    say "torch"

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

    No Comments

    Negative Logits
     Geneva
    -20.50
     Kuwait
    -18.13
     Fairfield
    -18.00
    Dub
    -17.88
     Alger
    -17.75
     Irving
    -17.75
     Cadillac
    -17.63
     Staten
    -17.63
    dateFormat
    -17.63
    .jquery
    -17.50
    POSITIVE LOGITS
     torch
    38.50
    (torch
    37.75
    torch
    37.00
    =torch
    34.75
     Torch
    32.75
     cuda
    25.00
     tensors
    24.38
     tensor
    23.50
    cuda
    23.13
     Tensor
    22.88
    Activations Density 0.108%

    No Known Activations