© 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. 1192
    Prev
    Next
    INDEX
    Explanations

    D variable

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Di
    -42.50
    Di
    -41.00
     Dynamic
    -39.75
    Dynamic
    -38.75
     DI
    -37.50
     dynamic
    -37.50
    ダイ
    -36.00
     Ди
    -35.50
     Dynamics
    -35.50
    DI
    -34.75
    POSITIVE LOGITS
    باح
    14.50
    ено
    14.00
    Motion
    13.81
     спорт
    13.81
    荆州
    13.56
    .twig
    13.50
    xCB
    13.44
    /engine
    13.38
    gnu
    13.00
    SBATCH
    12.94
    Activations Density 1.024%

    No Known Activations