© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48201
    Prev
    Next
    INDEX
    Explanations

    ego and self concepts

    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
    lah
    -0.10
    ians
    -0.09
    à¸Ļาà¸Ļ
    -0.09
    à¸ļุรี
    -0.08
    æľīåij³
    -0.08
    ively
    -0.08
    hift
    -0.08
    åĴĮçī¹çĤ¹
    -0.07
    å¾Ĺ主
    -0.07
    itud
    -0.07
    POSITIVE LOGITS
    ick
    0.08
    orning
    0.08
    al
    0.07
    ption
    0.07
    оÑĩи
    0.07
    æĤ¨åı¯ä»¥éĢļè¿ĩ
    0.07
    ä½Ĩæĺ¯ä¹Ł
    0.07
    lessness
    0.07
    conscious
    0.07
     volna
    0.07
    Activations Density 0.005%

    No Known Activations