© 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. 10311
    Prev
    Next
    INDEX
    Explanations

    XPath, futures, pedo**meters**

    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
    éĶ·
    -0.21
    èģ©
    -0.19
    祯
    -0.19
    åĴĮæľįåĬ¡
    -0.19
    æĿĤ
    -0.19
     vez
    -0.18
    енно
    -0.18
    è¾ĥ好
    -0.18
    esome
    -0.18
    鼾
    -0.18
    POSITIVE LOGITS
    ×ľ×ª
    0.20
    åī¥ç¦»
    0.20
    æĪ·åı£
    0.19
    cko
    0.18
    dpi
    0.18
    æ¦Ĥ念
    0.18
    bsp
    0.18
    lean
    0.18
    uelle
    0.18
    anko
    0.18
    Activations Density 0.079%

    No Known Activations