© 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. 15523
    Prev
    Next
    INDEX
    Explanations

    say "transform"

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

    No Comments

    Negative Logits
     taboo
    -18.00
    神话
    -16.75
    郦
    -16.75
    探访
    -16.75
    StringEncoding
    -16.63
     Legends
    -16.38
    疏导
    -16.25
    金属
    -16.25
     pepper
    -16.00
     Bronze
    -15.94
    POSITIVE LOGITS
     transform
    24.13
    <Transform
    24.13
    transform
    24.00
     transforms
    23.50
    	transform
    23.25
    .transform
    23.00
     transformations
    22.75
    -transform
    22.50
     vector
    22.13
     transformed
    22.00
    Activations Density 0.152%

    No Known Activations