© 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. 22748
    Prev
    Next
    INDEX
    Explanations

    first-person singular pronouns

    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
     conmigo
    -0.08
    ä»ĸèĩªå·±çļĦ
    -0.07
     himself
    -0.07
    abbo
    -0.07
    emper
    -0.07
     Saw
    -0.06
    è·ŁæĪij说
    -0.06
    lemn
    -0.06
     Ø®ÙĪدش
    -0.06
    ä»ĸæĥ³
    -0.06
    POSITIVE LOGITS
     ÙĨØŃÙĨ
    0.11
     ourselves
    0.08
    /us
    0.08
    æĪĸåħ¶ä»ĸ
    0.07
    zelf
    0.07
    urent
    0.07
    endi
    0.07
    æĪĸ对
    0.07
    çŃł
    0.07
    åĽłä¸ºæĪij们
    0.07
    Activations Density 0.683%

    No Known Activations