© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15375
    Prev
    Next
    INDEX
    Explanations

    say car

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

    No Comments

    Negative Logits
     plagiarism
    -18.00
     inventor
    -16.50
     infect
    -16.00
     Infect
    -15.75
     Xamarin
    -15.31
    Semantic
    -15.19
     plastics
    -15.19
    ubuntu
    -15.13
    invert
    -15.13
    /android
    -15.00
    POSITIVE LOGITS
    -car
    19.13
    car
    19.00
     car
    18.88
    吞
    18.63
    icken
    18.50
    wagon
    18.38
    (car
    17.88
    rides
    17.75
    Car
    17.63
    轿车
    17.38
    Activations Density 0.836%

    No Known Activations