© 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. 14808
    Prev
    Next
    INDEX
    Explanations

    dividing or combining parts

    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
    æīĢçĶ¨
    -0.07
    æľīçĽĬäºİ
    -0.06
     dép
    -0.06
     Daarna
    -0.06
    æīĢæ¶īåıĬ
    -0.06
    çŁ³æ¦´
    -0.06
    è¦ģçľĭ
    -0.06
    ä¸ŃæĮĩåĩº
    -0.06
    ÑĤÑĢо
    -0.06
    _join
    -0.06
    POSITIVE LOGITS
    å½¢æĪIJäºĨä¸Ģ个
    0.13
    å½¢æĪIJäºĨ
    0.12
    æݨåĩºäºĨ
    0.11
    å½¢æĪIJä¸Ģ个
    0.11
    å¼Ģåıijåĩº
    0.11
    ä¼ļæľīä¸Ģ个
    0.10
    产çĶŁäºĨ
    0.10
    建ç«ĭäºĨ
    0.10
    设计åĩº
    0.10
    ä¼ļ产çĶŁ
    0.09
    Activations Density 0.524%

    No Known Activations