© 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. 14932
    Prev
    Next
    INDEX
    Explanations

    action or status change

    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
    EDIA
    -0.08
    illah
    -0.08
    addOn
    -0.08
    ä¸įä»ħåľ¨
    -0.07
    ä¸įè¦ģ太
    -0.07
    ilarity
    -0.07
    é³´
    -0.07
    ÅĤadu
    -0.07
    鸣
    -0.07
     nemus
    -0.07
    POSITIVE LOGITS
     nor
    0.10
    æľ¬èº«
    0.10
     directly
    0.10
     direttamente
    0.09
     itself
    0.09
     directamente
    0.09
    缴æİ¥æĬĬ
    0.08
     diretamente
    0.08
    æĪĸ缴æİ¥
    0.08
    缴æİ¥çļĦ
    0.08
    Activations Density 0.074%

    No Known Activations