© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1003
    Prev
    Next
    INDEX
    Explanations

    say family

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

    No Comments

    Negative Logits
    氚
    -17.25
     \
↵
    -17.13
    讽
    -16.63
    梼
    -16.50
     дир
    -16.00
     Bundesliga
    -15.88
     doping
    -15.88
    BSD
    -15.88
    \
↵
    -15.81
     stadiums
    -15.75
    POSITIVE LOGITS
    的儿子
    21.88
     Samuel
    20.88
    庄园
    20.63
    CHILD
    20.25
     Margaret
    19.38
    Sarah
    19.38
     ancest
    19.25
    ughters
    18.88
     Sarah
    18.75
    儿子
    18.75
    Activations Density 0.190%

    No Known Activations