© 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. 63534
    Prev
    Next
    INDEX
    Explanations

    vegetarianism and legalization

    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
    ä¸įå¤ļ说
    -0.07
    γκ
    -0.07
    æĨ¬
    -0.07
    ares
    -0.06
    oom
    -0.06
    urve
    -0.06
    ä¸įèĥ½åĨį
    -0.06
    ôm
    -0.06
    ä¸įèĥ½ä½¿çĶ¨
    -0.06
    çº
    -0.06
    POSITIVE LOGITS
    ä¹Łæĺ¯ä¸ºäºĨ
    0.08
    ismus
    0.08
    æŃ¤ä¸¾
    0.08
    ollywood
    0.07
    æĽ´æľīåĪ©äºİ
    0.07
    éĹ®éĹ®
    0.07
    istas
    0.07
    éĻ¤éĿŀ
    0.07
    å¾Ĺè¿ĩ
    0.07
    æĥ¯äºĨ
    0.07
    Activations Density 0.137%

    No Known Activations