© 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. 754
    Prev
    Next
    INDEX
    Explanations

    say acronyms

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

    No Comments

    Negative Logits
     OSS
    -21.25
    太湖
    -20.50
    .hh
    -17.25
    蚌埠
    -17.13
     MPs
    -17.00
     GHC
    -16.88
    嵊
    -16.38
    崧
    -16.38
    硖
    -16.13
    .cc
    -16.00
    POSITIVE LOGITS
    是韩国
    20.13
    韩国
    18.63
    韩
    16.88
    蜚
    16.00
    外科
    14.94
    肤
    14.81
    剃
    14.69
    针
    14.69
    佯
    14.56
    咸阳
    14.38
    Activations Density 0.155%

    No Known Activations