© 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. 14176
    Prev
    Next
    INDEX
    Explanations

    say "ceramics"

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

    No Comments

    Negative Logits
    资源
    -22.75
    公共资源
    -21.88
    資源
    -20.63
    resources
    -19.38
     Psychology
    -19.38
     psychology
    -19.13
    _RESOURCES
    -18.75
     Resources
    -18.75
    ForResource
    -18.63
    Resources
    -18.38
    POSITIVE LOGITS
    陶瓷
    23.75
    窑
    23.50
     ceramic
    23.50
    釉
    23.50
     ceramics
    22.75
    瓷器
    21.63
     Ceramic
    20.63
    陶
    20.50
     pottery
    20.00
    瓷
    20.00
    Activations Density 0.193%

    No Known Activations