© 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. 16318
    Prev
    Next
    INDEX
    Explanations

    say discussion

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

    No Comments

    Negative Logits
     cray
    -18.63
     certifications
    -17.75
    inja
    -17.25
    证书
    -17.13
    -cert
    -17.00
    护照
    -16.75
     certify
    -16.50
    ewitness
    -16.25
    cert
    -16.00
     cert
    -15.75
    POSITIVE LOGITS
    讨论
    50.25
     discussion
    49.00
     discussions
    46.75
     Discussion
    45.00
    discussion
    43.50
    Discussion
    43.25
    討論
    41.00
     discuss
    39.50
     discussing
    39.25
     Discussions
    39.25
    Activations Density 0.338%

    No Known Activations