© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1731
    Prev
    Next
    INDEX
    Explanations

    oil

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

    No Comments

    Negative Logits
    石油
    -35.00
     Petroleum
    -30.88
     petroleum
    -29.50
    油气
    -28.75
    石油化工
    -27.38
     oil
    -27.25
     Oil
    -25.50
    油
    -24.50
     fossil
    -24.25
    Oil
    -23.75
    POSITIVE LOGITS
     brain
    15.81
    脑
    15.44
     browser
    15.06
     school
    14.94
    金
    14.81
    ListNode
    14.50
    学校
    14.50
     ListNode
    14.00
    -ln
    13.88
    .VK
    13.88
    Activations Density 0.092%

    No Known Activations