© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14966
    Prev
    Next
    INDEX
    Explanations

    say lake

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

    No Comments

    Negative Logits
    转移
    -19.13
    传输
    -18.63
    安装
    -17.63
    嵬
    -16.25
    install
    -16.25
    /trans
    -16.13
    GridLayout
    -16.13
     install
    -16.00
    방송
    -15.94
    audi
    -15.75
    POSITIVE LOGITS
    湖
    29.88
     lake
    29.25
    湖泊
    28.25
    湖区
    26.13
    lake
    25.88
     lakes
    25.75
    Lake
    25.75
     Lake
    24.00
     Lakes
    21.00
    淡水
    19.50
    Activations Density 0.114%

    No Known Activations