© 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. 26917
    Prev
    Next
    INDEX
    Explanations

    event transitions

    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
    pir
    -0.08
    /proto
    -0.07
    丹éĿĴ
    -0.07
     Zas
    -0.07
    ãģªãģĮãĤīãĤĤ
    -0.07
    åIJĮæŶåıĪ
    -0.07
     sto
    -0.07
    å·¥ä½ľçļĦåIJĮæŶ
    -0.07
    åIJİæĿ¥åıĪ
    -0.07
    åºĶ符åIJĪ
    -0.07
    POSITIVE LOGITS
     nanti
    0.10
    åľ¨åį³
    0.09
     ÙĪÙĤبÙĦ
    0.08
    rets
    0.07
    anton
    0.07
     post
    0.07
    çĤľ
    0.07
    Post
    0.07
    esz
    0.07
    åı£æīį
    0.06
    Activations Density 0.185%

    No Known Activations