© 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. 33339
    Prev
    Next
    INDEX
    Explanations

    people, particularly men

    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
    æijĴ
    -0.07
    è°¤
    -0.07
     kidding
    -0.07
    åľ¨è¿Ļ个ä¸ĸçķĮä¸Ĭ
    -0.07
    æĻĵæĺİ
    -0.07
    沿
    -0.07
     battleground
    -0.07
    gelegt
    -0.07
    ä¸Ģéģĵéģĵ
    -0.07
    -DD
    -0.06
    POSITIVE LOGITS
    åIJįåı«
    0.15
    åı«ä»Ģä¹Ī
    0.13
     bernama
    0.11
    åIJįåŃĹåı«
    0.10
    åı«
    0.10
    åı«åģļ
    0.10
    åIJį为
    0.10
     whose
    0.10
    whose
    0.09
    à¸Ĭืà¹Īà¸Ńวà¹Īา
    0.09
    Activations Density 0.201%

    No Known Activations