© 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. 2463
    Prev
    Next
    INDEX
    Explanations

    say "tube"

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

    No Comments

    Negative Logits
    提议
    -17.75
    乙
    -17.50
     Melissa
    -17.25
    提案
    -17.00
    Mel
    -17.00
    乙方
    -16.88
    Proposal
    -16.25
    PROP
    -15.69
    Eth
    -15.63
     proposal
    -15.50
    POSITIVE LOGITS
    管
    82.00
     tube
    73.00
     tubes
    65.50
     Tube
    64.00
     Tubes
    61.25
    Tube
    57.50
    tube
    56.75
     tub
    43.00
     tubing
    38.25
     pipe
    38.00
    Activations Density 0.169%

    No Known Activations