© 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
    2. Qwen3-1.7B
    3. 26-LLAMASCOPE-2-LORSA-16K-K64
    4. 324
    Prev
    Next
    INDEX
    Explanations

    fantasy

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

    No Comments

    Negative Logits
    华盛顿
    -24.00
    美国
    -23.88
    詹姆斯
    -23.63
    Clinton
    -23.50
    威廉
    -23.38
    毛泽东
    -22.88
    周恩来
    -22.75
    在美国
    -22.63
     Kennedy
    -22.50
     Clinton
    -22.38
    POSITIVE LOGITS
     dungeons
    18.38
     dracon
    17.75
    elves
    17.75
    精灵
    17.38
     Yug
    17.25
     elves
    17.00
     dru
    16.50
     dragons
    16.13
     ↵ ↵
    16.13
     Shadow
    15.75
    Activations Density 0.213%

    No Known Activations