© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 13910
    Prev
    Next
    INDEX
    Explanations

    say aid

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

    No Comments

    Negative Logits
    ệu
    -17.75
     sign
    -17.50
    (inv
    -16.75
    ImageView
    -16.38
    迹
    -16.00
     commanded
    -15.75
     command
    -15.75
     cmd
    -15.63
    binding
    -15.56
    edImage
    -15.44
    POSITIVE LOGITS
    补助
    22.00
    援助
    21.63
     aid
    20.13
    chemes
    19.63
     Aid
    19.25
     Assistance
    19.13
    补贴
    19.13
     distributions
    19.00
     assistance
    19.00
     distribution
    18.00
    Activations Density 0.512%

    No Known Activations