© 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. 16968
    Prev
    Next
    INDEX
    Explanations

    ENRON addresses

    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
    å¾½
    -0.20
    æĹ·
    -0.19
    夫
    -0.18
    ä¸ĢéĹª
    -0.18
    ild
    -0.18
    伤å¿ĥ
    -0.17
    oud
    -0.17
    åĴĮçĿ¦
    -0.17
    rand
    -0.17
    éģ½
    -0.17
    POSITIVE LOGITS
     Sylv
    0.20
    åįİ人
    0.18
     Germ
    0.18
    zego
    0.18
    ajar
    0.18
    ız
    0.17
    åĪ»
    0.17
    _MISS
    0.17
    èĭ±éĽĦ
    0.17
     slag
    0.17
    Activations Density 0.004%

    No Known Activations