© 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
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15518
    Prev
    Next
    INDEX
    Explanations

    say way

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

    No Comments

    Negative Logits
    esub
    -18.50
    胄
    -18.25
    usch
    -17.63
    esc
    -17.25
    iban
    -17.25
    omit
    -16.50
    oucher
    -16.38
    [offset
    -16.13
    opc
    -16.00
    uspend
    -15.81
    POSITIVE LOGITS
     path
    17.75
    .path
    17.38
    _Path
    16.88
    weg
    16.50
    _path
    16.00
    path
    15.63
    ldr
    15.38
    Path
    14.88
     Path
    14.75
    -path
    14.75
    Activations Density 0.007%

    No Known Activations