© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10532
    Prev
    Next
    INDEX
    Explanations

    wavelength ranges nm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    olist
    -0.21
    oria
    -0.21
    ÇŃ
    -0.21
    ABCDEFGHI
    -0.20
    .ur
    -0.20
    .Cap
    -0.20
    令
    -0.19
    :href
    -0.19
    индивид
    -0.19
    .Speed
    -0.19
    POSITIVE LOGITS
    ãĥļãĥĥãĥĪ
    0.24
     range
    0.23
    对人ä½ĵ
    0.21
    -range
    0.21
     ranges
    0.21
    常çĶ¨çļĦ
    0.21
    èĮĥåĽ´
    0.21
    宽带
    0.20
    å¹¿æ³Ľ
    0.20
     Arbitrary
    0.20
    Activations Density 0.184%

    No Known Activations