© 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. 62798
    Prev
    Next
    INDEX
    Explanations

    Under certain conditions (e.g., `Under`, `Reuters`, `TX`)

    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
    åįģç«ł
    -0.07
    æĽ´åĬłåĬªåĬĽ
    -0.07
    _INCLUDED
    -0.07
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    odata
    -0.07
     à¸ķà¸²à¸¡à¸Ľà¸£à¸°à¹Ģà¸łà¸Ĺ
    -0.07
    ierre
    -0.07
    æł¹æľ¬å°±ä¸į
    -0.07
     Cunning
    -0.07
     à¸ķามระà¸Ķัà¸ļ
    -0.07
    POSITIVE LOGITS
    æľĿ天
    0.07
    缣
    0.06
     Digit
    0.06
     ë§Īì¹ĺ
    0.06
    æľī家
    0.06
     ÄIJạt
    0.06
     ''.
    0.06
    说罢
    0.06
     Terl
    0.06
    صابات
    0.06
    Activations Density 0.243%

    No Known Activations