© 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. 3231
    Prev
    Next
    INDEX
    Explanations

    department

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    .bp
    -15.19
    牧
    -14.88
     DEM
    -14.31
    мес
    -14.00
    attern
    -13.94
    -dem
    -13.81
    ATIVE
    -13.75
     Dem
    -13.69
    heiro
    -13.69
    ayout
    -13.63
    POSITIVE LOGITS
     department
    89.50
    部门
    89.00
    department
    79.00
    Department
    75.50
     Department
    74.00
     departments
    71.00
    部門
    69.50
    .department
    65.50
    _department
    64.00
     Departments
    59.25
    Activations Density 0.177%

    No Known Activations