© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 3244
    Prev
    Next
    INDEX
    Explanations

    concept

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     treatment
    -22.25
    Treatment
    -20.75
     Treatment
    -19.88
     treatments
    -19.88
    SITE
    -18.75
     SITE
    -17.88
     Field
    -17.50
    Field
    -17.38
     treat
    -17.25
     treating
    -17.13
    POSITIVE LOGITS
     concept
    45.25
    概念
    43.00
    concept
    38.25
     Concept
    35.75
    Concept
    33.00
     concepts
    28.50
    的概念
    28.13
     Concepts
    25.00
    context
    23.88
     개념
    23.25
    Activations Density 0.154%

    No Known Activations