© 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. 15495
    Prev
    Next
    INDEX
    Explanations

    say gemstones

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

    No Comments

    Negative Logits
     suburb
    -18.75
     suburbs
    -17.75
    伞
    -17.50
    逆袭
    -17.38
    广场
    -16.63
     errorThrown
    -16.63
    痞
    -16.63
     weekends
    -16.50
     fortn
    -16.50
     backyard
    -16.38
    POSITIVE LOGITS
    _gem
    19.50
    糖
    19.25
    金刚
    18.88
    材
    18.75
    glas
    18.63
    Pow
    18.38
     Shine
    18.25
    玉石
    18.13
     Gem
    18.00
    材料
    18.00
    Activations Density 0.715%

    No Known Activations