© 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. 2959
    Prev
    Next
    INDEX
    Explanations

    say "wil"

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

    No Comments

    Negative Logits
    代
    -19.50
    [cur
    -19.38
    =num
    -18.50
     emulation
    -17.75
    曲
    -17.63
     Sim
    -17.38
     ser
    -17.38
    	cur
    -17.25
     emulate
    -17.25
     Maxim
    -17.13
    POSITIVE LOGITS
    Wil
    33.75
     Wil
    32.50
    万
    24.88
     wil
    22.63
    萬
    20.75
     Wiki
    19.38
     Wilkinson
    19.00
     Wik
    18.88
    Wik
    18.88
    万个
    17.88
    Activations Density 0.142%

    No Known Activations