© 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. 50195
    Prev
    Next
    INDEX
    Explanations

    is it a bug?

    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
    è¿Ŀæ³ķåĴĮä¸įèī¯
    -0.10
    æīĭæľºç«Ļ
    -0.08
    æħ§èģª
    -0.08
    åĿĩæĿ¥èĩªäºĴèģĶç½ij
    -0.07
    ãĥ¼ãĤ¸ãĥ¥
    -0.07
    åĨ²åĩ»
    -0.07
    oux
    -0.07
    ç²¾æ¹Ľ
    -0.07
    quo
    -0.07
    DeviceInfo
    -0.07
    POSITIVE LOGITS
    æĦıè§ģåıįé¦Ī
    0.08
    ìĿ´ê±°ëĤĺ
    0.07
    æĪijåıªèĥ½
    0.07
     tangg
    0.06
    ëĤĺ
    0.06
    zny
    0.06
     ожид
    0.06
    æĪĸèĢħæĺ¯
    0.06
    ness
    0.06
     nai
    0.06
    Activations Density 0.023%

    No Known Activations