© 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. 60784
    Prev
    Next
    INDEX
    Explanations

    secretly infiltrating or undercover operations

    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
    彤
    -0.07
    çĭĤæļ´
    -0.07
    ä¾Ŀ
    -0.07
    æīijéĿ¢èĢĮæĿ¥
    -0.07
    æĬ½è±¡
    -0.07
    éĵ¿éĶµ
    -0.07
    讼
    -0.06
    ابد
    -0.06
    çŃ
    -0.06
    æ¶Įçİ°
    -0.06
    POSITIVE LOGITS
    æļĹä¸Ń
    0.16
     secretly
    0.14
     stealth
    0.14
     covert
    0.14
     disguised
    0.14
    éļIJèĶ½
    0.14
    æĤĦæĤĦ
    0.14
    çļĦç§ĺå¯Ĩ
    0.14
    ç§ĺå¯Ĩ
    0.14
    éļIJèĹıçļĦ
    0.13
    Activations Density 0.205%

    No Known Activations