© 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. 41918
    Prev
    Next
    INDEX
    Explanations

    lists of countries, cities, or groups

    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
    åIJĦæĸ¹éĿ¢
    -0.08
    aw
    -0.07
    åIJİèĢħ
    -0.07
    æĭ¥
    -0.07
     edits
    -0.07
    åIJijèį£
    -0.07
    ç©¿çĿĢä¸Ģ
    -0.06
    åIJĦå¤Ħ
    -0.06
    arc
    -0.06
    iple
    -0.06
    POSITIVE LOGITS
    åĪĨåĪ«ä¸º
    0.15
    åĪĨåĪ«æĺ¯
    0.15
    åĪĨåĪ¥æĺ¯
    0.12
     namely
    0.12
    ä¾Ŀ次为
    0.10
     à¹Ħà¸Ķà¹īà¹ģà¸ģà¹Ī
    0.10
    ãĢģãĢģãĢģ
    0.10
    诸å¦Ĥ
    0.10
    ãĢģãĢģ
    0.10
     اÙĦØ«ÙĦاثة
    0.09
    Activations Density 0.271%

    No Known Activations