© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 524
    Prev
    Next
    INDEX
    Explanations

    say TB

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

    No Comments

    Negative Logits
     sailing
    -21.88
    赛车
    -21.25
     sail
    -21.00
     Sail
    -20.63
     paddle
    -20.00
    舰
    -19.88
     sailed
    -19.25
     Ferrari
    -19.25
     Corvette
    -19.00
    粽
    -18.88
    POSITIVE LOGITS
     TB
    37.25
    TB
    34.25
     Tub
    25.38
    _TB
    24.50
    (tb
    23.63
     tuberculosis
    22.88
     XB
    22.63
    tb
    21.88
     MB
    21.75
     tb
    21.13
    Activations Density 0.061%

    No Known Activations