© 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. 10882
    Prev
    Next
    INDEX
    Explanations

    even after

    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
    çĦ¡è«ĸ
    -0.09
    ä¸į论æĺ¯
    -0.09
    æĹłè®ºæĺ¯åľ¨
    -0.09
    çĦ¡è«ĸæĺ¯
    -0.09
     both
    -0.09
     zarówno
    -0.09
    _already
    -0.09
    both
    -0.08
    ä¸įè«ĸ
    -0.08
    ä¸įè«ĸæĺ¯
    -0.08
    POSITIVE LOGITS
     sekalipun
    0.13
    à¸ģà¹ĩà¸ķาม
    0.09
    ä¹Łä¸įä¾ĭå¤ĸ
    0.08
    olni
    0.08
    Except
    0.07
     ë§Īì°¬ê°Ģì§Ģ
    0.07
    å¦ĤèĬ±
    0.07
    ãģ§ãĤĤ
    0.07
    jam
    0.07
    س
    0.07
    Activations Density 0.113%

    No Known Activations