© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14096
    Prev
    Next
    INDEX
    Explanations

    say class

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

    No Comments

    Negative Logits
    软
    -17.00
    emat
    -16.50
    軟
    -16.38
    essim
    -15.56
     presses
    -15.19
     мяг
    -15.00
    布
    -14.81
     mềm
    -14.81
     submission
    -14.81
     run
    -14.81
    POSITIVE LOGITS
     class
    28.75
     Class
    28.25
     classes
    26.38
    Class
    25.38
    class
    25.13
     класс
    25.00
     classe
    24.63
     Interface
    24.25
     interfaces
    24.25
    -class
    24.13
    Activations Density 0.388%

    No Known Activations