© 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. 15733
    Prev
    Next
    INDEX
    Explanations

    say co

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

    No Comments

    Negative Logits
    (car
    -20.00
    Car
    -19.63
     car
    -19.50
    .Car
    -18.50
    PAR
    -18.50
     Car
    -18.25
     tongues
    -18.13
     CAR
    -17.88
    _CAR
    -17.63
    car
    -17.38
    POSITIVE LOGITS
     ко
    25.88
    co
    24.00
     co
    23.88
     Ко
    23.63
    -co
    23.50
     Co
    23.25
     coefficients
    23.13
     coefficient
    22.88
    coeff
    22.63
    _co
    22.50
    Activations Density 0.916%

    No Known Activations