© 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. 16977
    Prev
    Next
    INDEX
    Explanations

    what's newwhat's onwhat's upwhat's nextwhat workswhere are

    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
    .for
    -0.19
    rement
    -0.19
    orado
    -0.19
    æĦıæĦ¿
    -0.19
    à¸Ĥà¸Ļา
    -0.18
    .help
    -0.18
    æIJģ
    -0.18
    éģĺ
    -0.18
    æŁIJç§į
    -0.18
    isty
    -0.18
    POSITIVE LOGITS
    amac
    0.20
    ãģĤãģªãģŁãģ®
    0.18
    Dot
    0.18
    _finalize
    0.18
    Anim
    0.18
    æµĵæµĵ
    0.18
    æĪij家
    0.18
    Notify
    0.18
    dot
    0.17
    ãģĤãģªãģŁ
    0.17
    Activations Density 0.033%

    No Known Activations