© 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. 22139
    Prev
    Next
    INDEX
    Explanations

    comma followed by "I", "we", "you", or "the"

    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
     غÙĬرÙĩ
    -0.06
    åIJİ被
    -0.06
     otherwise
    -0.06
     respective
    -0.06
    olutely
    -0.06
    èĢĮä»ĸ
    -0.06
     Qu
    -0.06
    ä½łåij¢
    -0.06
     autrement
    -0.06
    èĢĮä¸Ķè¦ģ
    -0.06
    POSITIVE LOGITS
    jabi
    0.09
    以ä¸ĭåĩłçĤ¹
    0.09
    ëĿ¼ëıĦ
    0.09
    iore
    0.09
    ESTE
    0.09
    umer
    0.08
    æĪij们åı¯ä»¥
    0.08
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.08
     ÙģØ¥ÙĨ
    0.08
    以ä¸ĭæĺ¯ä¸ĢäºĽ
    0.08
    Activations Density 0.138%

    No Known Activations