© 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. 31001
    Prev
    Next
    INDEX
    Explanations

    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
    åIJĮæŶå°Ĩ
    -0.08
     одновÑĢеменно
    -0.08
    ä¾ĽåºĶ产åĵģ
    -0.08
    åIJĮæĹ¶å¯¹
    -0.08
    åľ¨è¿Ļç§į
    -0.07
     entonces
    -0.07
    ±
    -0.07
     sekaligus
    -0.06
     unborn
    -0.06
    以èĩ³
    -0.06
    POSITIVE LOGITS
     ÙĪÙĤبÙĦ
    0.12
     xong
    0.10
     selesai
    0.09
    å¾Įãģ¯
    0.09
    (after
    0.09
    æ´Ĺ礼
    0.08
     ÙĪبعد
    0.08
     usai
    0.08
    æīįçŁ¥éģĵ
    0.08
    à¸ľà¹Īาà¸Ļà¹Ħà¸Ľ
    0.08
    Activations Density 0.450%

    No Known Activations