© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 998
    Prev
    Next
    INDEX
    Explanations

    Georgian language

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

    No Comments

    Negative Logits
    纽约
    -21.88
     Doyle
    -21.63
     JFK
    -21.00
    在香港
    -20.75
    中美
    -20.38
     Cole
    -20.25
     Fairfield
    -20.13
     Manhattan
    -19.88
     Hudson
    -19.75
    洛杉矶
    -19.75
    POSITIVE LOGITS
     mb
    19.75
     mw
    19.25
     Sas
    19.13
    畲
    18.00
     gsi
    18.00
    drv
    17.63
     Assy
    17.50
     pw
    17.50
    mb
    17.38
    柞
    17.13
    Activations Density 0.022%

    No Known Activations