© 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. 39722
    Prev
    Next
    INDEX
    Explanations

    light and natural description

    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
    åħīèį£
    -0.09
    èī°èĭ¦å¥ĭæĸĹ
    -0.08
    æ»Ķæ»Ķ
    -0.08
    æĤ²æĥ¨
    -0.08
    avan
    -0.07
    ä¿ĿæĮģé«ĺ度
    -0.07
    大海
    -0.07
    沼泽
    -0.07
    æ¶ķ
    -0.07
    ç«ĭå¾·
    -0.07
    POSITIVE LOGITS
    è¢ħ
    0.08
    åħ¬åı¸æݨèįIJ
    0.08
    maj
    0.08
    æĺł
    0.08
    æ³»
    0.08
    ç¼ķ
    0.07
    æ¼¾
    0.07
    åijĪçİ°åĩº
    0.07
     casc
    0.07
    çĤ¹ç¼Ģ
    0.07
    Activations Density 0.050%

    No Known Activations