© 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. 14565
    Prev
    Next
    INDEX
    Explanations

    exercises and labs

    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
    åĪ«æĹł
    -0.07
    strt
    -0.06
    ame
    -0.06
     lam
    -0.06
     maps
    -0.06
    دÙĦ
    -0.06
    详
    -0.06
     pockets
    -0.06
    ä¸īåĪĨ
    -0.06
     Bull
    -0.06
    POSITIVE LOGITS
     exercises
    0.12
     Exercises
    0.11
    ç»ĥä¹ł
    0.10
    exercise
    0.10
     exercise
    0.10
     Exercise
    0.09
    å·©åĽº
    0.09
    Exercise
    0.09
    æĮijæĪĺ
    0.08
     quizzes
    0.08
    Activations Density 0.026%

    No Known Activations