© 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. 10440
    Prev
    Next
    INDEX
    Explanations

    pseudo- or -osis endings, drug names, medical conditions

    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
    æĬĹæ°§åĮĸ
    -0.21
    ë¶Ħ
    -0.20
     McKay
    -0.20
    è·Ĺ
    -0.19
    åģ¥åº·çļĦ
    -0.18
    wins
    -0.18
    æİīèIJ½
    -0.18
    çݯ
    -0.17
    äºĨå¾Īå¤ļ
    -0.17
    ä¸ĵç§ij
    -0.17
    POSITIVE LOGITS
    .opend
    0.21
    aal
    0.21
    cert
    0.21
    æ¯Ļ
    0.19
     Muse
    0.19
    ä¹ĺ
    0.19
     pseud
    0.19
     cert
    0.19
    æłĩé¢ĺ
    0.19
    ä»»ä½ķæŶåĢĻ
    0.18
    Activations Density 0.012%

    No Known Activations