© 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. 10459
    Prev
    Next
    INDEX
    Explanations

    MySQL replication

    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
    empre
    -0.21
    没æĶ¶
    -0.21
    çIJĨ解åĴĮ
    -0.21
     Sheldon
    -0.20
    æįį
    -0.19
    rary
    -0.19
    æķ´é¡¿
    -0.19
    çħĬ
    -0.19
     Sne
    -0.18
    åĮ£
    -0.18
    POSITIVE LOGITS
    家çĶ¨
    0.23
    priv
    0.19
    eshire
    0.19
    /apt
    0.19
    æ³Ĭ
    0.18
    æīĩ
    0.18
    inth
    0.18
    éı¡
    0.18
    èĤ¥
    0.17
    :length
    0.17
    Activations Density 0.009%

    No Known Activations