© 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. 63762
    Prev
    Next
    INDEX
    Explanations

    stage or job training

    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
    åĩºéŨ
    -0.09
     aloud
    -0.08
    åľ¨åľºçļĦ
    -0.08
    ä¹ĭä¸ĢçļĦ
    -0.08
     lẫn
    -0.08
    åĩºçİ°åľ¨
    -0.08
    çļĦåľºæīĢ
    -0.08
     gì
    -0.08
    æīĢåľ¨çļĦ
    -0.08
     entram
    -0.08
    POSITIVE LOGITS
    /on
    0.11
    /off
    0.11
    /out
    0.09
    èĨĽ
    0.08
    ãĤĴæŀľãģŁ
    0.08
     befind
    0.08
    abouts
    0.08
    /up
    0.08
    ä¸įä¹ħçļĦ
    0.07
    æĽ´çĶŁ
    0.07
    Activations Density 0.112%

    No Known Activations