© 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. 28728
    Prev
    Next
    INDEX
    Explanations

    named or called

    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
    bens
    -0.07
    æĺ¯ä¸Ģ段
    -0.07
    åıªæĺ¯ä¸Ģ
    -0.07
    æł¹æľ¬å°±æĺ¯
    -0.07
    ä¸įè¿ĩäºĨ
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    åı¯æĺ¯ä¸Ģ
    -0.07
    è¿ĺæĺ¯æľīäºĽ
    -0.07
    Boom
    -0.07
    %%%
    -0.07
    POSITIVE LOGITS
    åı«åģļ
    0.09
     appunto
    0.08
    åIJįåı«
    0.08
    åIJį为
    0.08
     названием
    0.08
     “
    0.07
    åIJįçĤº
    0.07
     namens
    0.07
    óf
    0.07
     "
    0.07
    Activations Density 0.253%

    No Known Activations