© 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. 24723
    Prev
    Next
    INDEX
    Explanations

    pronouns and names followed by actions

    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
    à¸ķà¸Ļ
    -0.07
    ä¸İ该
    -0.07
    该ä¼ģä¸ļ
    -0.07
    èº«åľ¨
    -0.07
    éĥ¨èIJ½å®¢
    -0.07
    该éĻ¢
    -0.07
     oneself
    -0.07
    帮åĬ©ä»ĸ
    -0.06
    inson
    -0.06
    身
    -0.06
    POSITIVE LOGITS
    æ¯ĶæĪij
    0.13
    æ¯ĶæĪij们
    0.13
    为æĪij
    0.13
    åĴĮæĪijä¸Ģèµ·
    0.12
    对æĪijçļĦ
    0.11
    è§ģæĪij
    0.11
    为æĪij们çļĦ
    0.11
    为æĪij们
    0.11
    对æĪij
    0.11
    éĻªæĪij
    0.11
    Activations Density 0.803%

    No Known Activations