© 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. 12587
    Prev
    Next
    INDEX
    Explanations

    Fall of, Text-Based Baseball, munch on, electroencephalograms, Somali children, Mountain Lion, parenteral nutrition, Mega drop down, Immunodeficiency Virus, total hip

    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
    ׼ף
    -0.07
    ãĤ§
    -0.06
    alla
    -0.06
     infância
    -0.06
    åĭī
    -0.06
    edException
    -0.06
    åı«ä»Ģä¹Ī
    -0.06
    ongsTo
    -0.06
    áĥļáĥĿáĥij
    -0.06
    erd
    -0.06
    POSITIVE LOGITS
    ãģ¨ãģĦãģ£ãģ¦ãĤĤ
    0.10
    åĮ¡
    0.08
    ilee
    0.07
    ãģ¨è¨Ģãģ£ãģ¦ãĤĤ
    0.06
    udd
    0.06
    æĪĸèĢħ说
    0.06
    ulu
    0.06
    ÑİÑĢа
    0.06
    å¸ĮæľĽå¯¹æĤ¨
    0.06
    æľīåĪ«
    0.06
    Activations Density 6.042%

    No Known Activations