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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 362
    Prev
    Next
    INDEX
    Explanations

    say "building" words

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

    No Comments

    Negative Logits
     Huawei
    -21.75
    华为
    -19.25
    鲲
    -18.75
    桂林
    -18.13
    Crypt
    -18.00
     Xin
    -17.88
    延安
    -17.63
     infected
    -17.50
    西藏
    -17.50
     Xia
    -17.38
    POSITIVE LOGITS
    建築
    16.13
    实物
    16.00
    厂房
    15.56
    건축
    15.50
     buildings
    15.50
    .bot
    15.50
    烧
    15.38
    门窗
    15.31
    建筑材料
    15.06
    建筑
    14.88
    Activations Density 0.089%

    No Known Activations