© 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. 1032
    Prev
    Next
    INDEX
    Explanations

    do not say allergy

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     allerg
    -25.63
     allergies
    -24.50
    _algo
    -24.13
     Algorithms
    -24.00
    Algorithm
    -23.75
     allergic
    -23.38
    算法
    -23.38
     allergy
    -23.25
     algorithms
    -23.13
     Algorithm
    -23.13
    POSITIVE LOGITS
    科教
    18.00
    科学
    15.69
    Pix
    15.56
    science
    15.38
     Pix
    15.19
     Science
    15.13
    Scient
    15.00
     science
    14.75
    Science
    14.63
    湘
    14.56
    Activations Density 0.061%

    No Known Activations