© 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. 64301
    Prev
    Next
    INDEX
    Explanations

    places, professions, and organizations

    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
    èĩªæĭĶ
    -0.08
    æĹłå¿Į
    -0.08
    çļĦå°ıç¼ĸ
    -0.08
    çIJ¦
    -0.07
    åħĦå¼Łå§IJ妹
    -0.07
     metre
    -0.07
    åħĪçŁ¥
    -0.07
    åħ¶éģĵ
    -0.07
    çĹħéŃĶ
    -0.07
     báºŃt
    -0.07
    POSITIVE LOGITS
    åIJįåı«
    0.09
     blah
    0.07
    ä¸Ģ个åı«
    0.07
    éĿłå·¦
    0.07
    人头
    0.07
     Stud
    0.06
    paro
    0.06
    æĮĩåIJį
    0.06
    rieve
    0.06
     unnamed
    0.06
    Activations Density 0.271%

    No Known Activations