© 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. 10684
    Prev
    Next
    INDEX
    Explanations

    fields and meadows

    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
    件
    -0.22
    æĪĴ
    -0.20
    稿
    -0.19
    海峡
    -0.19
    家ä¼Ļ
    -0.18
    outs
    -0.18
    geber
    -0.18
    hole
    -0.18
    å¥ģ
    -0.18
    ilig
    -0.17
    POSITIVE LOGITS
    çķĶ
    0.18
    shade
    0.18
     bÃło
    0.18
    尽头
    0.18
    éĩĮçļĦ
    0.17
    éĺ³åħī
    0.17
    ÑģÑĥ
    0.17
    _ble
    0.16
    RELEASE
    0.16
    ns
    0.16
    Activations Density 0.044%

    No Known Activations