© 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. 1517
    Prev
    Next
    INDEX
    Explanations

    say "geometry"

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

    No Comments

    Negative Logits
    信
    -43.50
     Faith
    -39.50
     faith
    -36.50
    信号
    -33.00
    signal
    -32.50
     signal
    -32.50
    信用
    -31.88
    faith
    -31.00
     Signal
    -29.88
    (signal
    -29.75
    POSITIVE LOGITS
    几何
    19.63
     geometric
    18.63
     geom
    18.63
     GE
    18.00
    IOC
    18.00
     Geometry
    16.75
    延安
    16.63
    auc
    15.75
     geometry
    15.50
     Mexico
    15.44
    Activations Density 0.109%

    No Known Activations