© 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. 1161
    Prev
    Next
    INDEX
    Explanations

    say "court"

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

    No Comments

    Negative Logits
     symbol
    -68.50
     Symbol
    -64.00
    符号
    -63.75
     symbols
    -63.50
    Symbol
    -62.75
    symbol
    -61.75
    -symbol
    -59.25
     Symbols
    -58.75
    _symbol
    -57.25
    symbols
    -56.75
    POSITIVE LOGITS
    fire
    17.13
     court
    16.75
     Court
    16.63
    court
    16.50
    ate
    16.00
    Court
    16.00
    火灾
    15.25
    oscope
    14.94
     COURT
    14.50
     Courts
    14.38
    Activations Density 0.097%

    No Known Activations