© 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. 1152
    Prev
    Next
    INDEX
    Explanations

    accounting

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

    No Comments

    Negative Logits
    会计
    -42.50
     accounting
    -37.75
     Accounting
    -37.50
     ACCOUNT
    -32.00
    Account
    -30.50
    <Account
    -30.38
     accountant
    -30.25
     account
    -30.13
    	account
    -29.63
     accountId
    -29.50
    POSITIVE LOGITS
    灯
    17.88
     Portugal
    16.25
    燈
    15.13
    酒
    14.50
     Europa
    14.50
    葡
    14.19
    .dart
    14.00
     Wine
    13.75
     wine
    13.75
     Port
    13.75
    Activations Density 0.059%

    No Known Activations