© 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. 1176
    Prev
    Next
    INDEX
    Explanations

    do not say corn

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

    No Comments

    Negative Logits
     corn
    -31.38
     Corn
    -27.38
    Corn
    -25.50
    corn
    -24.50
     maize
    -22.75
    玉米
    -22.63
     Cornell
    -21.50
    创新
    -19.00
     innovation
    -17.00
     sm
    -16.88
    POSITIVE LOGITS
     photographs
    18.25
    atabase
    17.25
     photograph
    16.38
     wavelength
    16.25
     bookstore
    16.13
     Photography
    15.88
    书店
    15.88
     wavelengths
    15.81
    数据库
    15.81
     Muse
    15.81
    Activations Density 0.070%

    No Known Activations