© 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. 16060
    Prev
    Next
    INDEX
    Explanations

    say heritage

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

    No Comments

    Negative Logits
    汽
    -22.00
     Huck
    -19.88
     carrot
    -19.50
    胡萝卜
    -19.38
     atm
    -19.25
    cars
    -19.00
     Mou
    -19.00
     Dew
    -18.88
     cars
    -18.63
    igator
    -18.38
    POSITIVE LOGITS
    宫廷
    19.00
    宏
    17.75
    全域
    17.50
    璋
    16.63
    大陆
    16.50
    文化遗产
    15.94
     palace
    15.94
    銀
    15.81
    ilver
    15.63
     Commonwealth
    15.56
    Activations Density 1.715%

    No Known Activations