© 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. 10623
    Prev
    Next
    INDEX
    Explanations

    critics and complaining

    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
    大家ä¸Ģèµ·
    -0.23
    Bid
    -0.22
     Bid
    -0.20
    åIJ¬è¯Ŀ
    -0.19
    ETO
    -0.19
    æĭĽ
    -0.19
    èĮ¸
    -0.19
    _bid
    -0.19
    chap
    -0.18
    èįļ
    -0.18
    POSITIVE LOGITS
    æĬĸ
    0.21
     lou
    0.20
    xin
    0.20
    æĮº
    0.19
    éĺ»
    0.19
    osas
    0.19
    è´¨çĸij
    0.19
    æijĪ
    0.19
    andal
    0.19
    ibel
    0.19
    Activations Density 0.048%

    No Known Activations