© 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. 860
    Prev
    Next
    INDEX
    Explanations

    say "east or west"

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

    No Comments

    Negative Logits
    刍
    -18.25
    贵州省
    -18.13
    阿根廷
    -18.00
     Guatemala
    -17.50
    canf
    -17.50
    漓
    -16.88
     Hugo
    -16.75
     GU
    -16.25
    綦
    -15.88
     Bolivia
    -15.69
    POSITIVE LOGITS
     East
    62.25
    东
    61.25
    East
    60.50
    東
    52.00
     east
    50.75
     EAST
    50.50
    east
    49.25
     West
    49.00
     west
    46.75
    West
    45.75
    Activations Density 0.353%

    No Known Activations