© 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. 9638
    Prev
    Next
    INDEX
    Explanations

    medical conditions and specific groups

    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
    大ä¸Ī夫
    -0.07
    afür
    -0.06
    ä»»
    -0.06
    åľ¨åħ¶ä¸Ń
    -0.06
     Mansion
    -0.06
    檬
    -0.06
    è¿Ļä¸Ģ次
    -0.06
    模æĿ¿
    -0.06
    两çĤ¹
    -0.06
    Benchmark
    -0.06
    POSITIVE LOGITS
    å°±æĺ¯åĽłä¸º
    0.11
    为ä»Ģä¹Īåij¢
    0.09
    ãģĹãģ°
    0.08
    为ä»Ģä¹Ī
    0.08
    æŃ£æĺ¯åĽłä¸º
    0.08
    常说çļĦ
    0.08
    çĤºä»Ģ麼
    0.08
    为åķ¥
    0.08
    çŃīçݰ象
    0.08
     why
    0.08
    Activations Density 0.188%

    No Known Activations