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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 27-LLAMASCOPE-2-LORSA-16K-K64
    7. 15985
    Prev
    Next
    INDEX
    Explanations

    say memory

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

    No Comments

    Negative Logits
    pike
    -17.13
    Government
    -16.88
    application
    -16.63
     LARGE
    -16.13
     government
    -15.94
    省政府
    -15.94
    Office
    -15.63
    Application
    -15.50
     Spartan
    -15.31
    DataService
    -15.31
    POSITIVE LOGITS
    的记忆
    19.13
    记忆
    19.00
    唯美
    18.13
    诗意
    18.00
    记录
    17.50
     Memory
    17.25
    月下
    17.25
    月
    17.00
    悸
    16.75
    吟
    16.63
    Activations Density 0.389%

    No Known Activations