© 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. 1332
    Prev
    Next
    INDEX
    Explanations

    say "远方"

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

    No Comments

    Negative Logits
     poetry
    -56.50
    诗
    -53.00
    詩
    -53.00
    诗歌
    -53.00
     Po
    -51.25
     Poetry
    -51.00
     poems
    -50.75
    Po
    -50.75
     poem
    -49.75
     poetic
    -49.00
    POSITIVE LOGITS
    Church
    16.75
     Churchill
    16.50
    _Window
    16.38
    Windows
    16.25
    switch
    16.25
     Europa
    16.13
    windows
    15.94
    Eu
    15.88
    window
    15.75
     Eu
    15.38
    Activations Density 0.184%

    No Known Activations