© 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. 35054
    Prev
    Next
    INDEX
    Explanations

    electromagnetic radiation and waves

    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
    redis
    -0.08
    ocache
    -0.08
     turnaround
    -0.07
    gebracht
    -0.07
    vene
    -0.07
    éļ¾æ±Ĥ
    -0.07
    bracht
    -0.07
    åĩºè´§
    -0.07
    æīĢå±ŀ
    -0.07
    åıĸèĪį
    -0.07
    POSITIVE LOGITS
     emitted
    0.13
     eman
    0.12
     waves
    0.10
     electromagnetic
    0.09
     invisible
    0.09
     radiation
    0.09
    çĶµç£ģ
    0.09
     rays
    0.09
    waves
    0.09
    è¾IJå°Ħ
    0.09
    Activations Density 0.102%

    No Known Activations