© 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. 9887
    Prev
    Next
    INDEX
    Explanations

    emotion regulation

    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
    ierte
    -0.08
    ÑĬÑĤ
    -0.08
    britann
    -0.08
    ä¸Ńæĸ¹
    -0.08
     Postar
    -0.07
    ãģ¤ãĤĤ
    -0.07
    å¼ķèµĦ
    -0.07
    ÑģÑĤоиÑĤ
    -0.07
    ÑĮÑĤе
    -0.07
    Streamer
    -0.07
    POSITIVE LOGITS
    Âł
    0.06
    âĢİ
    0.06
    iek
    0.06
    æĺ¯ä¸įå¤Ł
    0.05
    ookie
    0.05
    oes
    0.05
    edic
    0.05
    iskan
    0.05
     ↵
    0.05
    ç¿°
    0.05
    Activations Density 0.070%

    No Known Activations