© 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. 11472
    Prev
    Next
    INDEX
    Explanations

    waiting to deliver

    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
    以ä¸ĭæĸ¹å¼ı
    -0.09
     recurs
    -0.08
     _______,
    -0.08
    æľ¬åľºæ¯ĶèµĽ
    -0.08
    æľī以ä¸ĭ
    -0.07
     übrigens
    -0.07
    elop
    -0.07
     surpresa
    -0.07
    以ä¸ĭæŃ¥éª¤
    -0.07
    ãģ¾ãģĽãĤĵãģĮ
    -0.07
    POSITIVE LOGITS
     appunto
    0.09
     magari
    0.09
    æīįè¡Į
    0.08
    åıĪæĪĸèĢħ
    0.07
    éĤ£ä¸ªæŶåĢĻ
    0.07
    éĤ£æł·çļĦ
    0.07
    ä¸ĭä¸Ģç§Ĵ
    0.07
     whatever
    0.07
    ä¸ĭä¸ĢåĪ»
    0.07
    é¦
    0.06
    Activations Density 2.732%

    No Known Activations