© 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. 2801
    Prev
    Next
    INDEX
    Explanations

    say "bil"

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

    No Comments

    Negative Logits
    xis
    -16.50
    net
    -16.13
    idge
    -16.00
     MODIFY
    -16.00
    opsis
    -15.94
     Modi
    -15.88
    pery
    -15.75
     Modifier
    -15.69
     Net
    -15.19
    改造
    -15.13
    POSITIVE LOGITS
     Bil
    47.75
     bil
    43.75
    bil
    36.25
     bilateral
    29.88
    Mil
    29.75
     mil
    28.50
     mill
    26.63
    mil
    26.38
     Mil
    26.25
     mult
    24.38
    Activations Density 0.031%

    No Known Activations