© 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. 1293
    Prev
    Next
    INDEX
    Explanations

    [Y] => [yes]

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

    No Comments

    Negative Logits
    (sym
    -31.63
     sym
    -28.38
     PY
    -28.25
    𝑌
    -28.25
     Ye
    -27.88
     SY
    -26.88
     Sym
    -26.88
    sym
    -26.75
     Py
    -26.38
    _sym
    -26.25
    POSITIVE LOGITS
    Construction
    15.94
    .dialog
    14.50
     Construction
    14.38
    _SOCKET
    14.06
    gaard
    14.00
    sockets
    13.75
    osas
    13.19
     screen
    13.00
    afen
    12.94
     pol
    12.88
    Activations Density 0.815%

    No Known Activations