© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62760
    Prev
    Next
    INDEX
    Explanations

    happiness and well-being

    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¸įåĪ©
    -0.09
    å§ĭèĩ³
    -0.08
    æľīåĬĽ
    -0.08
    éĽĦåİļ
    -0.07
    å¸Īé£İ
    -0.07
    вÑıÑĤ
    -0.07
     Liability
    -0.07
     chÄĻt
    -0.07
    åĪ©å®³
    -0.07
     deadly
    -0.07
    POSITIVE LOGITS
     satisfaction
    0.12
    满æĦı
    0.11
    满æĦı度
    0.11
     happiness
    0.10
    ä¸į满æĦı
    0.10
     Satisfaction
    0.10
    æĦīæĤ¦
    0.10
    满足
    0.09
    满æĦıçļĦ
    0.09
    滿æĦı
    0.09
    Activations Density 0.075%

    No Known Activations