© 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. 14076
    Prev
    Next
    INDEX
    Explanations

    say architecture

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

    No Comments

    Negative Logits
    刺激
    -18.00
     hepat
    -16.13
    拉动
    -15.75
    管制
    -15.75
    サー
    -15.63
    票
    -15.56
    atasets
    -15.50
    ataset
    -15.44
    肝
    -15.00
    Liver
    -14.81
    POSITIVE LOGITS
    建筑
    45.50
     architectural
    43.25
     architecture
    41.75
    建筑设计
    41.00
    建筑师
    40.25
     Architecture
    39.50
    建築
    39.50
     buildings
    39.00
     Architect
    38.75
    Architecture
    38.25
    Activations Density 0.668%

    No Known Activations