© 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. 2676
    Prev
    Next
    INDEX
    Explanations

    say pot/tube

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

    No Comments

    Negative Logits
     temp
    -21.13
    .temp
    -20.38
    临时
    -19.88
    =temp
    -19.75
    孟
    -19.75
    TEM
    -19.38
    -temp
    -19.00
    Temp
    -18.50
    temp
    -18.38
    	temp
    -18.25
    POSITIVE LOGITS
    pot
    23.25
     Pot
    22.63
     pot
    22.13
     tube
    21.13
    Pot
    19.75
     tubes
    19.13
    库
    18.00
    tube
    17.63
    管
    17.38
    _pot
    17.25
    Activations Density 0.095%

    No Known Activations