© 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. 41883
    Prev
    Next
    INDEX
    Explanations

    stars ceiling panel

    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
    inian
    -0.08
    大é¢ĺ
    -0.07
    ä¸Ģå¸Ĩ
    -0.07
    æĶ¹è§Ĥ
    -0.06
     involving
    -0.06
    ilage
    -0.06
    ifice
    -0.06
    ocado
    -0.06
    ä¸Ģå¸Ĩé£İ顺
    -0.06
    å¤ļæĸ¹
    -0.06
    POSITIVE LOGITS
    æķ°éĩıåĴĮ
    0.14
    æķ°éĩı
    0.14
    æĢ»æķ°
    0.14
    æķ¸éĩı
    0.13
    æķ°çĽ®
    0.13
    éĹ´è·Ŀ
    0.12
    æİĴåĪĹ
    0.12
    æĢ»æķ°çļĦ
    0.12
    æķ°éĩı为
    0.12
    个æķ°
    0.12
    Activations Density 0.545%

    No Known Activations