© 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. 32072
    Prev
    Next
    INDEX
    Explanations

    first person pronoun

    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
     {*}
    -0.09
    PLIED
    -0.08
    plied
    -0.08
    iaux
    -0.08
    dued
    -0.08
     Crossing
    -0.08
    æĽ´å¤ļåĽŀçŃĶ
    -0.08
    lement
    -0.08
    ä¸įæĺ¯åIJĹ
    -0.07
    è©®
    -0.07
    POSITIVE LOGITS
     recall
    0.08
     insuff
    0.07
    夫åIJĽ
    0.07
    ª
    0.06
    RE
    0.06
    ETY
    0.06
    ATA
    0.06
    ami
    0.06
    ORK
    0.06
    idé
    0.06
    Activations Density 0.005%

    No Known Activations