© 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. 28270
    Prev
    Next
    INDEX
    Explanations

    foreign language text

    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
    åĴĮ马
    -0.07
    åıªè¦ģæĪij们
    -0.07
    åĩºäºĨ
    -0.06
    åĺĽ
    -0.06
    åĴĮåįİ
    -0.06
     By
    -0.06
    æĬĬå®ĥ
    -0.06
    æĬĬ她
    -0.06
    å¾Ĺå¤ļ
    -0.06
    åľ¨æĪij们
    -0.06
    POSITIVE LOGITS
    à¸Īร
    0.08
    åľ¨çº¿åĴ¨è¯¢
    0.08
    ubat
    0.08
    ounce
    0.07
    estos
    0.07
    ospel
    0.07
    puesta
    0.07
    ÑħождениÑı
    0.07
    该类
    0.07
    çľ¼åīįçļĦ
    0.07
    Activations Density 0.318%

    No Known Activations