© 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. 726
    Prev
    Next
    INDEX
    Explanations

    Water Margin

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

    No Comments

    Negative Logits
    芬兰
    -20.00
     fluores
    -18.88
     Libyan
    -18.75
    挪威
    -18.75
    伊斯
    -18.50
    加拿
    -18.25
    GCC
    -18.13
    加拿大
    -17.88
    洮
    -17.63
     Glas
    -17.50
    POSITIVE LOGITS
    郓
    23.13
    孙悟空
    20.88
    小说
    20.38
     yuan
    19.00
    曹操
    18.38
     Wu
    18.38
    剧本
    18.00
    戏曲
    17.88
    喜剧
    17.75
    武
    17.63
    Activations Density 0.079%

    No Known Activations