© 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. 447
    Prev
    Next
    INDEX
    Explanations

    conflict regions

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

    No Comments

    Negative Logits
    鄱
    -19.13
    YZ
    -19.13
    浔
    -18.63
     Ontario
    -18.25
    Yu
    -18.13
     Toronto
    -18.13
     Auschwitz
    -17.75
    nü
    -17.50
    南昌
    -17.50
    九江
    -17.38
    POSITIVE LOGITS
    阿富汗
    23.38
     Afghan
    23.00
     Afghanistan
    22.63
     Kabul
    18.88
    美军
    18.00
     Taliban
    17.75
     Iraqi
    17.25
    咸阳
    16.75
    伊拉克
    16.75
    演习
    16.50
    Activations Density 0.219%

    No Known Activations