© 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. 382
    Prev
    Next
    INDEX
    Explanations

    say "immune"

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

    No Comments

    Negative Logits
    民航
    -20.88
    童装
    -20.13
     samsung
    -19.38
    米粉
    -19.25
    高尔夫
    -19.13
    亚运会
    -18.38
     safari
    -18.25
    纱
    -17.88
    爆
    -17.63
    绿城
    -17.63
    POSITIVE LOGITS
    免疫
    33.00
     immun
    28.75
    风湿
    27.50
     Immun
    26.50
     Rhe
    26.25
     immune
    25.25
     rhe
    24.63
    -imm
    23.88
     arthritis
    23.50
    炎症
    22.38
    Activations Density 0.161%

    No Known Activations