© 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. 15786
    Prev
    Next
    INDEX
    Explanations

    => yl

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

    No Comments

    Negative Logits
    瀑布
    -21.88
    椿
    -20.63
    锦绣
    -20.50
     SEA
    -20.50
     Bounty
    -19.50
     Bauer
    -19.13
     Everest
    -19.00
    fish
    -18.88
    ottie
    -18.25
    丽江
    -18.25
    POSITIVE LOGITS
    角
    20.13
    -co
    18.63
    cos
    17.50
    _co
    17.00
    偏
    16.75
    (cos
    16.63
    -dr
    16.25
    coat
    16.25
     Co
    16.13
    .co
    16.13
    Activations Density 1.105%

    No Known Activations