© 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. 950
    Prev
    Next
    INDEX
    Explanations

    non‑Latin characters

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

    No Comments

    Negative Logits
    挪威
    -33.50
     Norwegian
    -32.00
     Norway
    -30.88
    青岛市
    -30.75
    青岛
    -30.25
     Icelandic
    -29.63
    北海
    -28.00
     Scandinavian
    -27.75
    鲁能
    -27.75
    潍坊
    -27.38
    POSITIVE LOGITS
    楚
    48.75
    河南省
    42.25
     Ohio
    39.00
    郑州
    38.25
     Kentucky
    37.25
    信阳
    37.00
     Egyptian
    37.00
    河南
    35.75
     SQLITE
    35.50
     Egyptians
    35.25
    Activations Density 0.825%

    No Known Activations

    This feature has no known activations.