© 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. 10473
    Prev
    Next
    INDEX
    Explanations

    extract entity name data

    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
    FilterWhere
    -0.20
     Brock
    -0.19
    etch
    -0.19
    acomment
    -0.19
    ê¶Į
    -0.19
     Worldwide
    -0.19
    -scrollbar
    -0.19
    esign
    -0.19
    .permissions
    -0.18
    .rad
    -0.18
    POSITIVE LOGITS
    æıIJåıĸ
    0.39
     extraction
    0.28
     extracted
    0.28
     Extraction
    0.27
    extract
    0.25
     Extract
    0.25
    æĮĸæİĺ
    0.25
     extracting
    0.24
     extractor
    0.24
    Extract
    0.24
    Activations Density 0.137%

    No Known Activations