© 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. 15008
    Prev
    Next
    INDEX
    Explanations

    absorbs/retains/traps/transports something

    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¸Ĭิà¸ĩ
    -0.07
    isd
    -0.07
    éĥģéĥģ
    -0.07
    æ¼¾
    -0.07
    æ»¡çľ¼
    -0.07
    åľ¨ä¸ŃåĽ½çļĦ
    -0.06
    olari
    -0.06
     ÙĦÙĦÙħÙĨ
    -0.06
    à¸ģารà¹ĥà¸Ĭà¹ī
    -0.06
    ä¸Ģ棵
    -0.06
    POSITIVE LOGITS
     incoming
    0.15
    incoming
    0.12
    Incoming
    0.11
     Incoming
    0.11
    æĿ¥èĩª
    0.09
    å¤ĸæĿ¥
    0.09
    åĴĮå¤ĦçIJĨ
    0.09
     outgoing
    0.08
     inbound
    0.08
    ä¾Ĩèĩª
    0.08
    Activations Density 0.364%

    No Known Activations