© 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. 31043
    Prev
    Next
    INDEX
    Explanations

    military units and legal 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
    åĪ©å¤ļ
    -0.08
     seo
    -0.07
    æ²¼
    -0.07
    صØŃ
    -0.07
    ä¼ijæģ¯ä¸Ģä¸ĭ
    -0.07
    çĩ¥
    -0.07
    æĦıå¤ĸçļĦ
    -0.07
    urat
    -0.07
    .exports
    -0.07
    æŃĩ
    -0.07
    POSITIVE LOGITS
     internal
    0.08
    éĩĩ纳
    0.08
    åĨħéĥ¨çļĦ
    0.08
    åĨħéĥ¨
    0.07
    çļĦäºĭä¸ļ
    0.07
     tenue
    0.07
    个人
    0.07
    XX
    0.07
    ä¸Ģ个åı«
    0.07
    æł¹æį®èĩªèº«
    0.07
    Activations Density 0.017%

    No Known Activations