© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47610
    Prev
    Next
    INDEX
    Explanations

    way for

    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
    çļĦ
    -0.09
    anas
    -0.08
    اÙĨات
    -0.08
    ın
    -0.08
    nya
    -0.07
    ÛĮ
    -0.07
    çļĦãģª
    -0.07
    Õ¸ÖĤÕ¶
    -0.07
    ainty
    -0.07
    Ãłn
    -0.07
    POSITIVE LOGITS
     for
    0.20
     длÑı
    0.18
    for
    0.18
     untuk
    0.17
     für
    0.17
    длÑı
    0.15
    สำหรัà¸ļà¸ģาร
    0.15
    	for
    0.15
     voor
    0.15
     براÛĮ
    0.15
    Activations Density 0.920%

    No Known Activations