© 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. 10624
    Prev
    Next
    INDEX
    Explanations

    have a

    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
    Not in Any Lists

    No Comments

    Negative Logits
    颢
    -0.22
     Æ°u
    -0.20
    obel
    -0.20
    éĶ´
    -0.19
    .idea
    -0.19
    ä¼ĺ
    -0.19
    pen
    -0.19
    ohn
    -0.19
    帮
    -0.19
    éŁ¿
    -0.19
    POSITIVE LOGITS
     dataset
    0.23
    两åıª
    0.22
    两个人
    0.21
     внеÑĪне
    0.21
     зÑĢ
    0.20
    å©»
    0.19
    两æĿ¡
    0.19
    ä¸Ģ群
    0.19
    è°ĥçļ®
    0.19
    ä¸Ģå®ļèĥ½
    0.19
    Activations Density 0.823%

    No Known Activations