© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 16378
    Prev
    Next
    INDEX
    Explanations

    say "heating"

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

    No Comments

    Negative Logits
    COL
    -19.38
    cold
    -18.13
     SKF
    -18.00
    -col
    -17.63
    NewLabel
    -17.38
    -Col
    -16.88
    	col
    -16.88
    冷却
    -16.75
    淀
    -16.50
     COL
    -16.13
    POSITIVE LOGITS
    煨
    17.50
    烘
    16.00
    采暖
    15.88
    加热
    15.50
     heating
    15.50
    ungan
    15.38
    raising
    14.94
    路
    14.81
    供暖
    14.81
     heaters
    14.69
    Activations Density 0.106%

    No Known Activations