© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 244
    Prev
    Next
    INDEX
    Explanations

    say "geographic terms"

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

    No Comments

    Negative Logits
    indexPath
    -17.75
    泣
    -15.94
    猗
    -15.69
    厂房
    -15.56
     Illinois
    -15.13
    闵
    -15.06
    唾
    -14.94
     RDD
    -14.94
    赣州
    -14.94
     Corpor
    -14.88
    POSITIVE LOGITS
     CAPITAL
    17.75
    cape
    17.38
     asia
    16.25
     land
    16.13
    _km
    16.00
    dv
    15.81
    Crime
    15.50
    地中
    15.38
     Crime
    15.38
    十字
    15.31
    Activations Density 0.341%

    No Known Activations