© 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. 2279
    Prev
    Next
    INDEX
    Explanations

    Method 2 – all TOKENS_AFTER_MAX_ACTIVATING_TOKEN are the same token “陶”. say 陶

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

    No Comments

    Negative Logits
    mut
    -20.00
     MUT
    -19.88
    互
    -19.38
     mutual
    -18.63
     Mutual
    -17.50
    _mut
    -17.00
    ems
    -16.50
    mutation
    -15.94
     وبين
    -15.50
     puls
    -15.38
    POSITIVE LOGITS
    陶
    70.50
    陶瓷
    38.75
     ceramic
    36.75
     Ceramic
    33.50
     pottery
    33.50
     ceramics
    32.75
     Tor
    31.88
     Cer
    31.63
    Tor
    30.88
     clay
    29.75
    Activations Density 0.046%

    No Known Activations