© 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. 14295
    Prev
    Next
    INDEX
    Explanations

    medical and biological 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
    Not in Any Lists

    No Comments

    Negative Logits
    æµģåĩº
    -0.21
    ä½łçŁ¥éģĵ
    -0.20
    éªĬ
    -0.19
    çĶ¨å¾®ä¿¡
    -0.18
    adal
    -0.18
    æ´ĭ
    -0.18
    æĺ¶
    -0.17
    bourg
    -0.17
    onus
    -0.17
    lemen
    -0.17
    POSITIVE LOGITS
    诸å¦Ĥ
    0.21
    errat
    0.20
    çħ½
    0.19
    ãĤĤãģĨ
    0.19
    æľīå¾Īå¤ļç§į
    0.18
    箸
    0.18
    çĽĺ
    0.17
     like
    0.17
    ä¸įæĸŃå¢ŀ强
    0.17
     Parl
    0.17
    Activations Density 0.276%

    No Known Activations