© 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. 10368
    Prev
    Next
    INDEX
    Explanations

    captain's name or role

    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
    onaut
    -0.18
    ä¼Ļä¼´
    -0.17
    ä¿Ŀå§Ĩ
    -0.17
    abouts
    -0.17
    Į
    -0.16
    羯
    -0.16
    äºĨä¸Ģä¸ĭ
    -0.15
    plode
    -0.15
    IRM
    -0.15
    oram
    -0.15
    POSITIVE LOGITS
    cies
    0.23
    cy
    0.20
    们
    0.17
    eer
    0.17
    ship
    0.17
    ned
    0.16
    们çļĦ
    0.16
    ëĭĺ
    0.16
    åĵ¡
    0.16
    wise
    0.16
    Activations Density 0.021%

    No Known Activations