© 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. 645
    Prev
    Next
    INDEX
    Explanations

    say GIS

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

    No Comments

    Negative Logits
    Trader
    -19.13
     coin
    -18.75
    -chat
    -18.63
     Coach
    -18.25
     Mentor
    -18.13
     sock
    -18.13
    动脉
    -18.13
    (Socket
    -18.00
    coin
    -17.88
     SOCKET
    -17.88
    POSITIVE LOGITS
    Terrain
    27.00
     GIS
    26.13
     terrain
    25.75
    地貌
    25.13
     Terrain
    25.00
    地理
    24.75
    地形
    24.63
    gis
    24.25
    GIS
    24.00
    terrain
    22.75
    Activations Density 0.186%

    No Known Activations