© 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. 50286
    Prev
    Next
    INDEX
    Explanations

    medical and scientific terms

    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
    åĿĩ为
    -0.08
    è¿Ļæĺ¯ä¸ª
    -0.07
    åĪĻæĺ¯
    -0.07
    身为
    -0.07
    è¿Ļæĺ¯ä¸Ģ个
    -0.07
    ä½ľçĤº
    -0.07
    æķ¦
    -0.07
    æīįæĺ¯çľŁæŃ£çļĦ
    -0.07
    çļĦéĥ½æĺ¯
    -0.07
    è¿Ļä¸įæĺ¯
    -0.07
    POSITIVE LOGITS
    å¹¿æ³ĽçĶ¨äºİ
    0.10
    ä¹ĭä¸Ģ
    0.09
    常çĶ¨äºİ
    0.08
    нка
    0.08
    主è¦ģçĶ¨äºİ
    0.08
    åħ¼
    0.07
     cuya
    0.07
    kke
    0.07
    Äįka
    0.07
     cuyo
    0.07
    Activations Density 0.597%

    No Known Activations