© 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. 1094
    Prev
    Next
    INDEX
    Explanations

    say science

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ALAR
    -19.50
     Security
    -19.13
    _AL
    -18.38
    URITY
    -18.25
    ALA
    -18.13
    Security
    -18.00
    AL
    -18.00
     security
    -17.50
    .AL
    -17.38
    _alg
    -17.13
    POSITIVE LOGITS
     science
    19.75
    script
    18.88
    scientific
    17.75
    Script
    17.50
     script
    17.38
    科学
    17.38
     scientific
    17.25
    science
    17.25
     Script
    16.13
     Science
    15.81
    Activations Density 0.202%

    No Known Activations