© 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. 14481
    Prev
    Next
    INDEX
    Explanations

    sleep and being asleep

    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
     tát
    -0.08
    سخ
    -0.07
    å©¿
    -0.07
    æĺĮ
    -0.07
    ULK
    -0.07
    Holder
    -0.07
     fizz
    -0.07
     lá»Ļc
    -0.07
    reto
    -0.07
    ×¥
    -0.07
    POSITIVE LOGITS
    åħ¥çĿ¡
    0.17
     sleep
    0.16
    çĿ¡çľł
    0.15
    çĿ¡å¾Ĺ
    0.15
    çĿ¡è§ī
    0.15
    çľł
    0.15
    Sleep
    0.15
    sleep
    0.15
    æŀķ头
    0.15
     sleeping
    0.15
    Activations Density 0.108%

    No Known Activations