© 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. 38478
    Prev
    Next
    INDEX
    Explanations

    modern science and medicines

    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
    ä¸įæĪIJ
    -0.08
    æĮīçħ§è§Ħå®ļ
    -0.08
    IDI
    -0.08
    没è¿ĩ
    -0.08
    åĩºçİ°è¿ĩ
    -0.08
    forcer
    -0.07
    hoe
    -0.07
    åĩºçı¾äºĨ
    -0.07
    æĿ¾äºĨä¸Ģåı£æ°Ķ
    -0.07
    ås
    -0.07
    POSITIVE LOGITS
     modern
    0.11
    çݰ代
    0.11
    æĺ¯çݰ代
    0.10
    çݰ代çļĦ
    0.10
    ç§ijåѦçļĦ
    0.10
    çļĦçݰ代
    0.10
     moderna
    0.09
     moderno
    0.09
     scientific
    0.09
     Modern
    0.09
    Activations Density 0.081%

    No Known Activations