© 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. 786
    Prev
    Next
    INDEX
    Explanations

    say asbestos

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

    No Comments

    Negative Logits
    在广州
    -25.88
    鳄
    -22.88
    广州
    -22.13
    南昌
    -21.75
    广州市
    -21.50
    在深圳
    -21.50
    醴
    -20.50
    趵
    -20.50
     bart
    -19.88
    豕
    -19.88
    POSITIVE LOGITS
     asbestos
    37.00
     fibers
    27.75
    纤维
    27.25
     Alban
    26.25
     fiber
    26.13
     Fib
    26.00
    fib
    25.25
     fib
    25.00
     AS
    24.75
    bestos
    24.13
    Activations Density 0.022%

    No Known Activations