© 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. 17276
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating types of military units or historical expeditions

    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
    (floor
    -0.22
    anners
    -0.20
    ocz
    -0.20
    ido
    -0.20
    dling
    -0.19
    à®±
    -0.19
    å¹²æ¶ī
    -0.19
    _migration
    -0.19
    ä¸ĢèĦļ
    -0.19
    æŁ±
    -0.19
    POSITIVE LOGITS
    ä¹ĭæĹħ
    0.26
    æ¯ı人
    0.22
    éļı
    0.22
    纡
    0.21
    ä¸ĩ人
    0.19
     DESC
    0.19
    æĹħç¨ĭ
    0.19
    åģľ
    0.18
    æ¯ı个人
    0.18
    è¡Įç¨ĭ
    0.18
    Activations Density 0.005%

    No Known Activations