© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1946
    Prev
    Next
    INDEX
    Explanations

    say cloud

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

    No Comments

    Negative Logits
    蔬菜
    -33.25
     vegetables
    -32.25
     vegetable
    -30.00
    菜
    -29.00
     Vegetable
    -28.63
    veget
    -25.00
    白菜
    -24.63
     Veget
    -24.13
    socket
    -22.00
    	socket
    -21.50
    POSITIVE LOGITS
    云
    24.25
     cloud
    23.13
    雲
    21.88
     innovate
    20.88
     clouds
    20.63
    LOUD
    20.38
    cloud
    20.00
    云端
    19.25
    Cloud
    19.25
     Cloud
    18.13
    Activations Density 0.170%

    No Known Activations