© 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. 7825
    Prev
    Next
    INDEX
    Explanations

    recognizing or understanding states of mind

    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
    ारà¥į
    -0.07
    æĬijæĪĸ
    -0.07
    æݪæīĭä¸įåıĬ
    -0.07
     lẻ
    -0.07
    è¿Ļæł·çļĦ人
    -0.07
    Wildcard
    -0.07
    太éļ¾
    -0.07
    æĵħéķ¿çļĦ
    -0.07
    ëıħ
    -0.07
    çŀĴ
    -0.07
    POSITIVE LOGITS
    认è¯ĨåĪ°
    0.11
    并æİ¥åıĹ
    0.09
    çľĭå¾ħ
    0.09
     mindset
    0.09
    çļĦå¿ĥæĢģ
    0.09
    æıIJéĨĴèĩªå·±
    0.08
     accepting
    0.08
    çIJĨ解
    0.08
    å¿ĥæĢģ
    0.08
     recognizing
    0.08
    Activations Density 0.117%

    No Known Activations