© 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. 21569
    Prev
    Next
    INDEX
    Explanations

    pronouns interacting with others

    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
    åĮĸ管çIJĨ
    -0.07
    对åŃ¦æł¡
    -0.07
    对
    -0.06
    åĴĮçī¹çĤ¹
    -0.06
    对客æĪ·
    -0.06
    è¢ģ
    -0.06
    Fcn
    -0.06
     lẫn
    -0.06
    ibility
    -0.06
    åĴĮä½ľçĶ¨
    -0.06
    POSITIVE LOGITS
    nish
    0.09
    anness
    0.09
    anner
    0.08
    zyw
    0.07
    çļĦä¸Ģçīĩ
    0.07
     behalf
    0.07
    luv
    0.07
    utsch
    0.07
    书åŁİ
    0.07
    stem
    0.07
    Activations Density 0.187%

    No Known Activations