© 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. 146
    Prev
    Next
    INDEX
    Explanations

    university names

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

    No Comments

    Negative Logits
    摩托车
    -19.75
     Oilers
    -17.63
     STOCK
    -17.50
     Lomb
    -17.38
    _STOCK
    -17.13
    农牧
    -17.00
     ATV
    -16.50
     OT
    -16.38
    消费者的
    -16.25
     Cowboys
    -16.13
    POSITIVE LOGITS
    清华大学
    39.50
    清华
    36.75
    北京大学
    34.00
    浙江大学
    31.63
     Harvard
    30.38
    哈佛
    29.63
     Beijing
    27.63
     Liu
    27.25
     Wu
    27.13
    在北京
    27.00
    Activations Density 0.266%

    No Known Activations