© 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. 25732
    Prev
    Next
    INDEX
    Explanations

    news article

    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
    èĥ¸
    -0.08
    åĴ³
    -0.06
    /LICENSE
    -0.06
    ç½ijåıĭä¸Ĭä¼ł
    -0.06
    illis
    -0.06
     minecraft
    -0.06
    ç¹ģéĩį
    -0.06
    urchased
    -0.06
    £¼
    -0.06
     orally
    -0.06
    POSITIVE LOGITS
     article
    0.11
    æĬ¥éģĵ
    0.10
     journalist
    0.10
    -article
    0.10
    /article
    0.10
     journalistic
    0.09
    éŁ
    0.09
    åł±éģĵ
    0.09
     report
    0.09
    æĸĩç«ł
    0.09
    Activations Density 0.723%

    No Known Activations