© 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. 367
    Prev
    Next
    INDEX
    Explanations

    say "character"

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

    No Comments

    Negative Logits
     Gujar
    -18.88
    丝绸
    -18.25
    .Mobile
    -18.13
    瓯
    -18.13
    EMU
    -18.00
    茶园
    -17.75
    ydro
    -17.63
    茶叶
    -17.63
    ��
    -17.50
    宁波
    -17.50
    POSITIVE LOGITS
    该剧
    20.38
    剧中
    20.13
     characters
    19.75
     Chuck
    19.13
     actor
    19.13
    演员
    19.00
    角色
    18.75
     character
    18.25
     Barney
    18.25
     Howard
    17.63
    Activations Density 0.160%

    No Known Activations