© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15784
    Prev
    Next
    INDEX
    Explanations

    say account

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

    No Comments

    Negative Logits
     Cove
    -17.25
    idf
    -16.63
    锦标
    -16.63
    簸
    -16.63
    agle
    -16.63
    窜
    -16.38
    竞价
    -16.25
    빅
    -16.13
    Invoker
    -16.00
    dio
    -15.38
    POSITIVE LOGITS
     account
    37.75
     accounts
    36.50
    账户
    35.75
    Account
    34.25
    account
    34.00
     Account
    33.50
    accounts
    33.00
    <Account
    33.00
     ACCOUNT
    33.00
     Accounts
    32.25
    Activations Density 0.147%

    No Known Activations