© 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. 21772
    Prev
    Next
    INDEX
    Explanations

    optical physics, ray tracing, Monte Carlo

    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
    çĶ¨ä¸Ĭ
    -0.09
     volatile
    -0.08
    anine
    -0.08
    寡
    -0.08
    漩
    -0.08
    æº
    -0.08
    RING
    -0.07
    åĸĺæģ¯
    -0.07
     Freeze
    -0.07
     burdens
    -0.07
    POSITIVE LOGITS
    åħī线
    0.10
     ray
    0.10
     rays
    0.10
     propagation
    0.10
     specular
    0.09
    å°Ħ
    0.09
    åħīåѦ
    0.09
     optical
    0.08
    çļĦä¼łæĴŃ
    0.08
    æķ£å°Ħ
    0.08
    Activations Density 0.005%

    No Known Activations