© 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. 17163
    Prev
    Next
    INDEX
    Explanations

    separators and subsequent terms

    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
     (
    -0.21
    -0.21
    çļĦ
    -0.20
    [
    -0.20
    :
    -0.20
    ↵↵
    -0.19
    (
    -0.19
    **
    -0.18
    *
    -0.18
    æĺ¯
    -0.17
    POSITIVE LOGITS
    phans
    0.35
    acles
    0.29
    /or
    0.28
    ients
    0.26
    thon
    0.23
     ÐŁÐ¾Ñĩем
    0.23
    lando
    0.23
    ifice
    0.21
    fully
    0.21
    ities
    0.21
    Activations Density 0.078%

    No Known Activations