© 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. 3140
    Prev
    Next
    INDEX
    Explanations

    say "."

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    治疗方法
    -17.13
     post
    -16.63
    政府
    -15.69
     treatment
    -15.19
     government
    -15.13
    条件
    -14.88
    区政府
    -14.81
    'post
    -14.50
    /post
    -14.38
     treatments
    -14.31
    POSITIVE LOGITS
     .
    25.00
     Structure
    19.88
     structure
    18.38
     figure
    17.38
     Model
    17.00
     model
    17.00
     modeled
    16.88
    -figure
    16.75
    model
    16.75
     point
    16.75
    Activations Density 0.352%

    No Known Activations