© 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. 1580
    Prev
    Next
    INDEX
    Explanations

    say "knife"

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

    No Comments

    Negative Logits
     Federal
    -36.75
    联邦
    -36.50
     federal
    -36.25
    Federal
    -35.75
     Feder
    -25.25
     федер
    -25.00
     Fed
    -23.13
     federally
    -23.00
    Fed
    -22.88
    -header
    -22.50
    POSITIVE LOGITS
     knife
    20.50
    刀
    19.25
     knives
    18.13
     innovation
    17.50
     Knife
    15.94
    knife
    15.88
     Kun
    15.38
     Knight
    15.19
     innovate
    15.06
     Sword
    14.63
    Activations Density 0.083%

    No Known Activations