© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3044
    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
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æŃ»èĢħ
    -0.25
    icio
    -0.24
    wear
    -0.23
     chết
    -0.23
    Areas
    -0.22
    ecute
    -0.22
     idi
    -0.22
     ÑģÑĤÑĢаÑħов
    -0.21
    icios
    -0.21
    athlon
    -0.21
    POSITIVE LOGITS
     waves
    0.34
     photons
    0.33
    æĿŁ
    0.33
     electromagnetic
    0.32
     rays
    0.32
     wave
    0.32
    æ³¢
    0.31
     Waves
    0.30
     radiation
    0.30
    æĸĩæĺİ
    0.30
    Activations Density 0.072%

    No Known Activations