© 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. 11218
    Prev
    Next
    INDEX
    Explanations

    negative emotions like resentment and disappointment

    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
    åĨłçĬ¶çĹħæ¯Ĵ
    -0.07
    åѦéĻ¢éĻ¢éķ¿
    -0.07
    chal
    -0.07
    忧æĤ£
    -0.06
    à¹Ģà¸Ľà¸¥
    -0.06
    olf
    -0.06
    çīµ
    -0.06
    chers
    -0.06
    ä¼łçļĦ
    -0.06
     seamlessly
    -0.06
    POSITIVE LOGITS
     resentment
    0.10
    åıįæĬĹ
    0.09
     distrust
    0.09
    æ¿Ģ
    0.09
    æĦ¤
    0.08
    æĬ¥å¤į
    0.08
    åıįåĩ»
    0.08
     cyn
    0.08
     disillusion
    0.08
    æĹłå¿ĥ
    0.08
    Activations Density 0.067%

    No Known Activations