© 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. 15470
    Prev
    Next
    INDEX
    Explanations

    say "topic"

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

    No Comments

    Negative Logits
    orte
    -16.13
     loss
    -15.88
    ilage
    -15.63
    赢
    -15.00
    庑
    -14.94
    asant
    -14.75
    古城
    -14.44
    梯
    -14.19
    atform
    -14.13
     Loss
    -14.06
    POSITIVE LOGITS
    主题
    49.00
     topic
    47.00
     topics
    46.50
     Topic
    45.75
    topic
    44.25
    Topic
    44.00
    的主题
    43.25
    topics
    42.00
     Topics
    41.50
     theme
    41.00
    Activations Density 0.388%

    No Known Activations