© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34868
    Prev
    Next
    INDEX
    Explanations

    optical light communication

    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
    Negative Logits
    ä¸ĭåİ»äºĨ
    -0.07
    adir
    -0.07
    çĻ¾å·Ŀ
    -0.07
    èĤ¥å¤§
    -0.06
    istar
    -0.06
    adona
    -0.06
    å¦Ĥå±±
    -0.06
    è¤
    -0.06
    lungs
    -0.06
    .pad
    -0.06
    POSITIVE LOGITS
     optical
    0.12
     Optical
    0.11
    çļĦåħī
    0.11
    åħīåѦ
    0.11
    åħīçļĦ
    0.10
    åħī
    0.10
     wavelengths
    0.10
    æ³¢éķ¿
    0.10
     wavelength
    0.10
    ê´ij
    0.10
    Activations Density 0.062%

    No Known Activations