© 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. 17054
    Prev
    Next
    INDEX
    Explanations

    all about

    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
    ä»»ä½ķä¸Ģ个
    -0.24
    æĽ´å¤ļ
    -0.23
     hẳn
    -0.22
    èĭ¥å¹²
    -0.21
    ä»»ä½ķ
    -0.20
    éĥ¨åĪĨåĨħ容
    -0.20
    ä¸ĢäºĽ
    -0.19
    alto
    -0.19
    å¾Īæľī
    -0.18
     лÑİбой
    -0.18
    POSITIVE LOGITS
    zers
    0.20
    agna
    0.19
    iance
    0.18
    adin
    0.18
    ergic
    0.18
     uLocal
    0.18
    itude
    0.17
    meal
    0.17
    ина
    0.17
    æģ¯
    0.17
    Activations Density 0.005%

    No Known Activations