© 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. 15927
    Prev
    Next
    INDEX
    Explanations

    say applications

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

    No Comments

    Negative Logits
    Girls
    -15.63
    飲み
    -15.31
    诛
    -15.13
    girls
    -14.75
     girls
    -14.25
    :params
    -14.25
    deliver
    -13.88
    女孩子
    -13.81
    secret
    -13.69
     coords
    -13.63
    POSITIVE LOGITS
    推广应用
    21.38
    应用
    20.25
    科研
    18.75
    研究
    18.63
    应用于
    18.38
    研究人员
    18.13
    发展
    17.63
    国际贸易
    17.38
    国际市场
    17.38
    技术
    17.38
    Activations Density 0.352%

    No Known Activations