© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11772
    Prev
    Next
    INDEX
    Explanations

    urgent or emergency followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oret
    -0.10
    累累
    -0.08
    itional
    -0.08
    ë§ģ
    -0.08
    æ®Ĩå°½
    -0.08
    à¸Ńà¸Ł
    -0.08
    åĽŀåij³æĹłç©·
    -0.08
    ειÏĦοÏħÏģγ
    -0.07
    resenter
    -0.07
    áĥ¯
    -0.07
    POSITIVE LOGITS
    urgent
    0.11
     urgent
    0.11
    紧迫
    0.11
    æĢ¥
    0.11
    à¸Ķà¹Īวà¸Ļ
    0.10
    ç´§æĢ¥
    0.10
    åħ³å¤´
    0.10
     urgente
    0.10
     urgency
    0.10
    ä¹ĭæĢ¥
    0.10
    Activations Density 0.073%

    No Known Activations