© 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. 14168
    Prev
    Next
    INDEX
    Explanations

    say "geography"

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

    No Comments

    Negative Logits
    =target
    -17.38
    狙
    -17.25
     target
    -17.25
     Targets
    -16.75
     APPLE
    -16.38
    门诊
    -16.13
    -target
    -15.81
    validation
    -15.63
     targets
    -15.56
    Targets
    -15.44
    POSITIVE LOGITS
    地理
    40.25
     geography
    37.00
     Geography
    35.00
     geographical
    34.00
     geographic
    32.75
     Geographic
    31.75
     GEO
    30.00
     Ge
    30.00
    Ge
    29.88
     geo
    29.75
    Activations Density 0.317%

    No Known Activations