© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 14228
    Prev
    Next
    INDEX
    Explanations

    say departments

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pattern
    -15.88
    ứng
    -15.44
    peaker
    -15.31
     pattern
    -15.19
     ngữ
    -15.13
     열
    -15.06
    Pattern
    -15.06
    ymbols
    -14.94
    _patterns
    -14.88
    膺
    -14.75
    POSITIVE LOGITS
    部门
    30.38
    职能部门
    29.13
     department
    29.00
     departments
    27.00
     staff
    27.00
    departments
    27.00
    员工
    26.25
    department
    26.13
    各部门
    25.50
     division
    25.38
    Activations Density 0.628%

    No Known Activations