© 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. 46781
    Prev
    Next
    INDEX
    Explanations

    peaceful, calm

    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
    毫ä¸įçĬ¹è±«åľ°
    -0.08
    Bold
    -0.07
     bold
    -0.07
    ä¸įåı¯éģ¿åħįåľ°
    -0.07
    æĸ¹ä¾¿
    -0.07
    gars
    -0.07
    æµĵ缩
    -0.07
     dramatic
    -0.07
    eltas
    -0.07
    æĭĵ
    -0.07
    POSITIVE LOGITS
     calm
    0.11
     Ñģпокой
    0.11
     peaceful
    0.11
     Спо
    0.11
    ç¼ĵåĴĮ
    0.11
    å¹³åĴĮ
    0.11
    å¹³éĿĻ
    0.11
    Ñģпо
    0.10
     peacefully
    0.10
     calming
    0.10
    Activations Density 0.280%

    No Known Activations