© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14483
    Prev
    Next
    INDEX
    Explanations

    HTML markup

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

    No Comments

    Negative Logits
     sinc
    -19.00
     vic
    -17.75
    ustin
    -17.13
    ymi
    -16.50
    horn
    -16.50
    uki
    -16.50
    ught
    -16.38
    .Sync
    -16.13
    ZN
    -16.13
    bach
    -15.94
    POSITIVE LOGITS
    eda
    20.25
    еле
    19.75
    sed
    18.88
     Dee
    18.50
    oble
    18.50
    elle
    18.25
    odel
    18.13
    ipple
    18.00
     Kel
    17.75
    eel
    17.75
    Activations Density 0.924%

    No Known Activations