© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 721
    Prev
    Next
    INDEX
    Explanations

    Arabic‑Indic digits

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

    No Comments

    Negative Logits
    济宁
    -33.50
     Finnish
    -32.50
    菏泽
    -31.13
     Danish
    -30.00
    黟
    -28.50
     Indonesian
    -28.13
    波兰
    -28.13
     Finland
    -28.13
    丹麦
    -27.63
     Copenhagen
    -27.50
    POSITIVE LOGITS
    ACE
    23.00
    (redis
    20.13
    三峡
    19.25
    河西
    19.00
     ACE
    18.88
     McKay
    18.88
     iceberg
    18.75
    .redis
    18.50
    荆州
    18.13
    骝
    18.13
    Activations Density 0.202%

    No Known Activations