© 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. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 378
    Prev
    Next
    INDEX
    Explanations

    say "Wilson"

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

    No Comments

    Negative Logits
     Egyptian
    -19.75
     HM
    -18.63
    楚
    -18.50
    汨
    -18.00
    مصر
    -17.50
     مصر
    -16.63
    HM
    -16.50
     Egyptians
    -16.50
    亚运
    -16.50
     المصرية
    -16.38
    POSITIVE LOGITS
     Wilson
    24.38
    Wilson
    22.25
     WI
    21.88
    小狗
    20.13
    WI
    18.25
     Weiner
    17.88
     Hubbard
    17.63
    木耳
    17.63
    狗
    17.38
    OfWork
    16.75
    Activations Density 0.018%

    No Known Activations