© 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. 61044
    Prev
    Next
    INDEX
    Explanations

    complementary pairs or sequences

    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
    åĬłæĭ¿å¤§
    -0.11
    æĸ°åĬłåĿ¡
    -0.10
    aikan
    -0.09
    unami
    -0.09
    ation
    -0.09
    ëģĶ
    -0.09
    ÑģÑĮ
    -0.09
    berry
    -0.09
    ly
    -0.09
    à§įত
    -0.09
    POSITIVE LOGITS
    äºĨ
    0.12
    ä½Ĩä¸įéĻIJäºİ
    0.10
    Ù°
    0.09
    kannya
    0.09
    çĦ¶æĺ¯
    0.08
    hone
    0.08
    ê¶ĮìĹIJ
    0.08
    æĪĸå¤ļ个
    0.07
    æĪij代表
    0.07
    她表示
    0.07
    Activations Density 0.002%

    No Known Activations