© 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. 2558
    Prev
    Next
    INDEX
    Explanations

    tube

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

    No Comments

    Negative Logits
     Ep
    -19.50
    Ep
    -19.38
    ,var
    -19.00
     var
    -18.88
    var
    -18.38
     ep
    -18.25
     Var
    -18.00
    (ep
    -18.00
    ,ep
    -17.13
    Var
    -17.00
    POSITIVE LOGITS
     tube
    45.50
     Tube
    44.50
    Tube
    44.50
    tube
    41.75
     tubes
    38.75
     Tubes
    38.25
     tubing
    24.63
     Tabs
    24.13
    tab
    23.50
    tabs
    23.50
    Activations Density 0.042%

    No Known Activations