© 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. 15538
    Prev
    Next
    INDEX
    Explanations

    say transplant

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

    No Comments

    Negative Logits
    耙
    -16.75
    egrator
    -16.75
    区委
    -16.38
    闭
    -16.25
    回馈
    -16.13
    зор
    -16.13
     UIImage
    -16.00
    .ast
    -15.88
    策略
    -15.75
    anno
    -15.69
    POSITIVE LOGITS
    苗
    23.63
     trans
    21.88
    	trans
    21.63
    trans
    21.50
    (trans
    20.38
    -trans
    20.25
    /trans
    20.25
    Trans
    20.13
    .trans
    19.88
     transplant
    19.88
    Activations Density 0.127%

    No Known Activations