© 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. 2006
    Prev
    Next
    INDEX
    Explanations

    graph

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

    No Comments

    Negative Logits
    图
    -58.25
     graph
    -56.00
    圖
    -51.75
     graphs
    -51.50
    graph
    -50.00
     GRAPH
    -49.00
     图
    -48.25
     Graph
    -48.25
    Graph
    -47.25
    图为
    -46.00
    POSITIVE LOGITS
     Legal
    15.44
    bü
    14.44
     Rockefeller
    14.44
     legal
    14.25
    .psi
    14.00
    违法行为
    14.00
    违法
    13.63
    legal
    13.63
    煤炭
    13.63
    SW
    13.25
    Activations Density 0.126%

    No Known Activations