© 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. 21504
    Prev
    Next
    INDEX
    Explanations

    personal and self reference

    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
    ream
    -0.07
    ç«
    -0.07
    omal
    -0.07
    ãĥ¼ãĥ«
    -0.07
    िला
    -0.07
     Luciano
    -0.06
    ennon
    -0.06
    彤
    -0.06
    maar
    -0.06
    ideon
    -0.06
    POSITIVE LOGITS
    èĩªèº«
    0.17
    èĩªèº«çļĦ
    0.14
     himself
    0.13
     personally
    0.13
    ä»ĸèĩªå·±
    0.12
    ä»ĸèĩªå·±çļĦ
    0.12
    èĩªå·±ä¹Ł
    0.12
     own
    0.12
    æľ¬èº«
    0.12
    æľ¬èº«çļĦ
    0.12
    Activations Density 0.626%

    No Known Activations