© 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. 647
    Prev
    Next
    INDEX
    Explanations

    say mask

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

    No Comments

    Negative Logits
     Mohammad
    -21.50
    zik
    -20.88
    西安
    -20.63
    Yii
    -20.00
     muslim
    -19.88
    伊斯兰
    -19.88
     Sultan
    -19.38
     Abbas
    -19.38
    陕西
    -19.38
    大唐
    -19.25
    POSITIVE LOGITS
     masks
    18.00
    (mask
    17.25
    getDb
    17.13
    面具
    16.88
     Cv
    16.88
     Mask
    16.75
    dbe
    16.63
    mask
    16.50
    	mask
    16.38
     mask
    16.13
    Activations Density 0.089%

    No Known Activations