© 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. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14346
    Prev
    Next
    INDEX
    Explanations

    say "cl"

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

    No Comments

    Negative Logits
    茧
    -17.00
     Zach
    -16.38
    (arc
    -16.25
    utar
    -16.13
    ucker
    -16.00
    _arc
    -16.00
     uz
    -15.81
    itel
    -15.75
    烤
    -15.75
    spir
    -15.69
    POSITIVE LOGITS
    -cl
    23.63
    Cla
    21.88
     Cl
    20.88
    .Cl
    20.75
    (cl
    20.38
    cl
    19.38
    	cl
    19.00
    클
    18.88
     кли
    18.25
    climate
    18.00
    Activations Density 0.952%

    No Known Activations