© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1960
    Prev
    Next
    INDEX
    Explanations

    say "mag"

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

    No Comments

    Negative Logits
    枪
    -21.25
    槍
    -20.00
     ar
    -18.25
    消防
    -16.25
    (ar
    -16.25
     tool
    -16.25
    UserCode
    -15.38
    芬兰
    -14.63
     Greeks
    -14.50
    [token
    -14.44
    POSITIVE LOGITS
     alphabet
    18.63
    磁
    18.63
     GEO
    18.00
     magnetic
    17.63
     geography
    17.63
     magnet
    17.50
     graphs
    17.25
     Magnet
    16.88
     comput
    16.63
     computational
    16.50
    Activations Density 0.316%

    No Known Activations