© 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. 14257
    Prev
    Next
    INDEX
    Explanations

    vote

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

    No Comments

    Negative Logits
    中心城市
    -19.75
    鹖
    -19.00
    信息服务
    -18.50
    地图
    -18.38
     visita
    -18.25
    服务体系
    -17.38
    服务
    -17.13
    的地图
    -16.88
     SERVICE
    -16.88
    json
    -16.88
    POSITIVE LOGITS
    票
    25.25
    决议
    24.25
     voted
    23.00
     vote
    22.88
     votes
    22.38
     approvals
    22.38
    Vote
    21.75
     approval
    21.38
    vote
    21.25
    批准
    20.38
    Activations Density 0.443%

    No Known Activations