© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1662
    Prev
    Next
    INDEX
    Explanations

    [literary] => [literary]

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

    No Comments

    Negative Logits
    文学
    -48.50
     literature
    -47.50
     Literature
    -45.75
    文學
    -43.25
     literary
    -40.50
    Liter
    -40.50
     liter
    -36.75
    liter
    -35.00
     Literary
    -34.75
    -liter
    -34.00
    POSITIVE LOGITS
    window
    16.25
    _tokens
    15.88
     window
    15.81
    windows
    15.75
     token
    15.56
     windows
    15.38
    	token
    15.38
    Tokens
    14.94
    窗
    14.69
    token
    14.63
    Activations Density 0.077%

    No Known Activations