© 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. 2293
    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
     reg
    -19.50
    pot
    -17.25
    Ver
    -17.13
     Ver
    -17.00
     regs
    -16.88
     Jess
    -16.75
     regist
    -16.50
     pot
    -16.50
    entic
    -16.00
     dict
    -15.25
    POSITIVE LOGITS
     pole
    28.63
     curve
    28.63
     Pole
    27.00
     poles
    25.38
    曲线
    24.50
     Curve
    24.38
    curve
    24.13
     curves
    24.00
    Curve
    23.50
    pole
    23.38
    Activations Density 0.292%

    No Known Activations