© 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. 10508
    Prev
    Next
    INDEX
    Explanations

    travel disruptions

    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
    china
    -0.23
    ildo
    -0.21
    TOR
    -0.20
    使çĶ¨èĢħæĪĸ
    -0.19
    abox
    -0.19
     Osborne
    -0.19
    ecast
    -0.18
     Morales
    -0.18
    arkan
    -0.18
    _SCOPE
    -0.18
    POSITIVE LOGITS
    åIJŀ
    0.22
    延误
    0.20
    æľ¬ç«Ļ
    0.19
    æİ¨è¿Ł
    0.19
    é§IJ
    0.19
    åİĨå¹´
    0.19
    severity
    0.19
    çģŀ
    0.19
     Stick
    0.19
    ç¬ŀ
    0.19
    Activations Density 0.003%

    No Known Activations