© 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. 15717
    Prev
    Next
    INDEX
    Explanations

    say change

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

    No Comments

    Negative Logits
    烧
    -20.63
    燒
    -17.88
    icket
    -16.13
    俸
    -15.31
    禄
    -14.69
    挹
    -14.56
    穴
    -14.50
     catchError
    -14.50
    风景区
    -14.50
    latlong
    -14.44
    POSITIVE LOGITS
    变化
    44.75
    变换
    44.50
     transformation
    43.75
    转变
    43.25
     change
    43.00
    变革
    43.00
    改变
    41.75
     Change
    41.50
     changes
    41.25
     transformations
    41.00
    Activations Density 0.756%

    No Known Activations