© 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. 2444
    Prev
    Next
    INDEX
    Explanations

    say "curve"

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

    No Comments

    Negative Logits
     Modal
    -17.38
     modal
    -17.25
    /modal
    -17.13
     CAP
    -17.00
    modifier
    -16.25
    modal
    -15.94
    CAP
    -15.88
    Modal
    -15.44
    -modal
    -14.56
     modifier
    -14.25
    POSITIVE LOGITS
    曲
    67.50
     �
    41.75
     curve
    38.00
    	cur
    38.00
    (cur
    37.75
    曲线
    36.75
     cur
    36.75
     curves
    36.00
    [cur
    35.75
    curve
    33.00
    Activations Density 0.032%

    No Known Activations