© 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. 20
    Prev
    Next
    INDEX
    Explanations

    Hungarian

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

    No Comments

    Negative Logits
    iston
    -17.88
    澎湃新闻
    -17.50
     Astronomy
    -16.50
    景德镇
    -16.38
    舟山
    -16.25
    荞
    -15.94
    乳业
    -15.69
    大豆
    -15.50
    人参
    -15.38
    大米
    -15.06
    POSITIVE LOGITS
     sz
    31.25
     Sz
    30.75
    (sz
    30.63
    .sz
    28.50
    Sz
    28.38
    _sz
    27.38
     Hungarian
    26.88
     az
    26.38
    isz
    25.63
     Ez
    25.13
    Activations Density 0.019%

    No Known Activations