© 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. 48361
    Prev
    Next
    INDEX
    Explanations

    last or final item

    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
    staan
    -0.09
    éĩįçĤ¹æĺ¯
    -0.08
    wana
    -0.07
    çªĺ
    -0.07
    =((
    -0.07
    QUI
    -0.07
    åīį两天
    -0.07
    hra
    -0.07
    à¹ģà¸Īà¸ĩ
    -0.07
    ãĥ¬ãĤ¹ãĥĪ
    -0.06
    POSITIVE LOGITS
    ä¹Łæĺ¯æľĢ
    0.08
     among
    0.08
    åĪ«æĹł
    0.08
    ä¹ĭä¸Ģ
    0.08
    among
    0.08
    å¸ļ
    0.07
    ä»»ä½ķåħ¶ä»ĸ
    0.07
    olin
    0.07
    æѤ类
    0.07
     darn
    0.07
    Activations Density 0.192%

    No Known Activations