© 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. 46729
    Prev
    Next
    INDEX
    Explanations

    has existed for

    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
    å±ĬæŶ
    -0.09
    ä¸ĭä¸Ģ次
    -0.09
    å½ĵä¸ĭ
    -0.09
    ä¸ĭ次
    -0.09
    å½ĵæŶçļĦ
    -0.08
    æľīä¸Ģ天
    -0.08
    å°ĨæĿ¥
    -0.08
    éĤ£æŶçļĦ
    -0.08
    åīįä¸Ģ天
    -0.08
    æѤæŶçļĦ
    -0.08
    POSITIVE LOGITS
     since
    0.14
     lately
    0.13
    以ä¾Ĩ
    0.12
    since
    0.11
    been
    0.11
    以æĿ¥
    0.11
    以æĿ¥çļĦ
    0.11
    _since
    0.11
     ÙħÙĨØ°
    0.11
     siden
    0.11
    Activations Density 1.474%

    No Known Activations