© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14799
    Prev
    Next
    INDEX
    Explanations

    say "geo" words

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

    No Comments

    Negative Logits
    翰
    -17.25
    kke
    -16.13
    osas
    -15.75
     mdl
    -15.75
    ՚
    -15.69
     Hust
    -14.63
    aub
    -14.38
    initializer
    -14.19
     Cosby
    -14.06
    instant
    -13.38
    POSITIVE LOGITS
    _geo
    22.38
     ge
    22.13
     geography
    21.13
    地理
    21.00
    高地
    20.63
    geo
    20.63
     geo
    19.38
    _geom
    18.50
    .geo
    18.00
    地处
    18.00
    Activations Density 0.132%

    No Known Activations