© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 192
    Prev
    Next
    INDEX
    Explanations

    say "epic"

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

    No Comments

    Negative Logits
     thermometer
    -18.75
    .temperature
    -18.75
     Rotterdam
    -18.25
    _party
    -18.00
    镍
    -17.88
    石膏
    -17.25
     Chem
    -17.00
    金陵
    -17.00
    argent
    -16.88
     Tiles
    -16.50
    POSITIVE LOGITS
     epic
    17.50
     Fib
    16.63
     Od
    16.38
     tale
    16.00
     Milton
    15.75
    Od
    14.94
    sgi
    14.69
     tales
    14.63
     bard
    14.63
    孙悟空
    14.44
    Activations Density 0.179%

    No Known Activations