© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1234
    Prev
    Next
    INDEX
    Explanations

    county

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

    No Comments

    Negative Logits
    会计
    -22.25
    fiber
    -21.63
    account
    -21.13
    县公安局
    -20.88
    Account
    -20.75
     account
    -20.63
    County
    -20.38
     fiber
    -20.13
     Account
    -20.00
    jpeg
    -20.00
    POSITIVE LOGITS
    金属
    19.00
     metal
    18.13
    舟
    17.38
    虹桥
    16.13
    芽
    15.94
    .Graph
    15.81
    欧洲
    15.56
     European
    15.56
     Bridges
    15.31
     metals
    15.19
    Activations Density 0.080%

    No Known Activations