© 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. 15848
    Prev
    Next
    INDEX
    Explanations

    say secrets

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

    No Comments

    Negative Logits
     Integration
    -17.00
     Integrated
    -16.88
     integration
    -16.63
    恽
    -16.63
    Extent
    -16.25
     Integr
    -16.00
     Shia
    -15.75
    .Entities
    -15.56
    สง
    -15.50
    掃
    -15.44
    POSITIVE LOGITS
     Trick
    20.75
    法宝
    20.25
    秘
    18.50
     keys
    18.13
    keys
    18.00
    窍
    17.75
    秘诀
    17.75
    KeyId
    17.63
    秘密
    17.63
    KeyName
    17.38
    Activations Density 0.230%

    No Known Activations