© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 2806
    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
    注
    -17.63
    .Annotation
    -17.50
     Annotation
    -17.25
     Zuk
    -17.13
     Mut
    -17.00
    (annotation
    -17.00
    (tab
    -16.88
    (mut
    -16.75
    _mut
    -15.94
    	tab
    -15.88
    POSITIVE LOGITS
     Cer
    64.00
     cer
    56.00
    cer
    51.25
    陶瓷
    41.00
     ceramic
    38.75
     Ceramic
    36.25
    cert
    34.75
     ceramics
    34.50
    Cert
    32.25
    陶
    31.50
    Activations Density 0.051%

    No Known Activations