© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1718
    Prev
    Next
    INDEX
    Explanations

    do not say fiber

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

    No Comments

    Negative Logits
    纤维
    -54.00
     fiber
    -52.75
     Fiber
    -51.75
     fibre
    -49.50
    fiber
    -49.25
     fibers
    -48.00
     Fib
    -46.50
     fib
    -44.25
    fib
    -43.00
    光纤
    -41.00
    POSITIVE LOGITS
     Game
    17.00
     Gui
    15.75
     GAME
    15.75
    Game
    15.50
     Psych
    15.38
    avid
    15.31
     Gulf
    15.25
     STATS
    15.19
     acc
    14.94
    Ps
    14.94
    Activations Density 0.092%

    No Known Activations