© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 15635
    Prev
    Next
    INDEX
    Explanations

    say path

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

    No Comments

    Negative Logits
    _shell
    -18.63
     shells
    -18.25
    inia
    -17.13
    (shell
    -16.75
    shell
    -16.50
     shell
    -16.50
    iesta
    -16.50
    .support
    -16.00
    ritz
    -15.44
     Shell
    -15.38
    POSITIVE LOGITS
    路径
    64.50
     path
    63.50
    path
    60.00
     paths
    59.50
     Path
    59.00
    Path
    55.75
    -path
    54.25
    paths
    54.00
     PATH
    53.75
     Paths
    53.75
    Activations Density 0.717%

    No Known Activations