© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12151
    Prev
    Next
    INDEX
    Explanations

    .CompilerServices, .widget, .app, .Fragment, .tbl, .h, .Co

    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
    ç®
    -0.19
    by
    -0.19
    [f
    -0.18
    [
    -0.18
    ä¹İ
    -0.18
     sing
    -0.18
    less
    -0.18
    (
    -0.17
    !
    -0.17
     evident
    -0.17
    POSITIVE LOGITS
     fkk
    0.23
    _ComCallableWrapper
    0.22
    é«ĺ峰论åĿĽ
    0.22
     najbli
    0.20
    æĭ¼åij½
    0.20
     newcom
    0.20
    åıį驳
    0.20
    ç¾İ好çĶŁæ´»
    0.19
    ä½£éĩij
    0.19
    人人éĥ½
    0.19
    Activations Density 0.951%

    No Known Activations