© 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. 17097
    Prev
    Next
    INDEX
    Explanations

    worm and related creatures

    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
    olland
    -0.23
    orary
    -0.19
    å¼±åĬ¿
    -0.19
    æĪij说
    -0.18
    毫ä¸įçĬ¹è±«
    -0.17
    riz
    -0.17
    绣
    -0.17
    æľ¦èĥ§
    -0.16
    æķ´åIJĪ
    -0.16
    çĭĻåĩ»
    -0.16
    POSITIVE LOGITS
     khá»ıi
    0.21
    estre
    0.20
    est
    0.20
     khúc
    0.20
    豸
    0.19
    ÑĤки
    0.19
    gle
    0.19
     toes
    0.18
    èĽĨ
    0.18
    led
    0.17
    Activations Density 0.012%

    No Known Activations