© 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. 3207
    Prev
    Next
    INDEX
    Explanations

    treatment

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    tsx
    -16.63
     module
    -16.13
    模块
    -16.00
    rtle
    -15.88
     board
    -15.63
    ョ
    -15.50
    zt
    -15.00
    tp
    -14.94
     Module
    -14.69
    uts
    -14.50
    POSITIVE LOGITS
     treatment
    86.00
     Treatment
    78.50
    Treatment
    77.50
     treatments
    70.00
     treat
    63.00
    治疗
    61.75
     treated
    59.50
     Treat
    59.25
     treating
    57.75
     treats
    51.00
    Activations Density 0.438%

    No Known Activations