© 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. 2423
    Prev
    Next
    INDEX
    Explanations

    say cur

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

    No Comments

    Negative Logits
    legs
    -20.50
     Legs
    -19.38
    Leg
    -18.00
     Glasses
    -17.50
    -leg
    -17.13
     filament
    -17.00
     Legisl
    -16.88
    树枝
    -16.75
     LEG
    -16.75
    lein
    -16.00
    POSITIVE LOGITS
     cur
    33.00
    (cur
    29.25
    Cur
    28.75
    cur
    28.75
     Cur
    28.75
    	cur
    26.50
    曲
    25.88
     curry
    24.50
    [cur
    23.63
    -cur
    22.38
    Activations Density 0.014%

    No Known Activations