© 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. 64167
    Prev
    Next
    INDEX
    Explanations

    optical modulation

    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
    鼨åŃ£
    -0.07
    zysta
    -0.07
     بÙĨدÛĮ
    -0.06
    è¾ĥæĹ©
    -0.06
    Ŀ¼
    -0.06
    èĥļ
    -0.06
    .frames
    -0.06
    è¾Ĺ转
    -0.06
    æĸ½å·¥åĽ¾
    -0.06
     лом
    -0.06
    POSITIVE LOGITS
     Optical
    0.10
     modulation
    0.09
     optical
    0.09
    è°ĥåĪ¶
    0.09
    ä»ĭ
    0.08
    æĶ¹åıĺ
    0.08
    çĶµä¿¡
    0.08
    ponse
    0.08
    åħīåѦ
    0.08
     changes
    0.08
    Activations Density 0.075%

    No Known Activations