© 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. 10578
    Prev
    Next
    INDEX
    Explanations

    cold, viral, respiratory infections

    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
    èĵij
    -0.21
    æ¶Įåħ¥
    -0.20
    å®īç½®
    -0.19
     ticking
    -0.19
    åĿĽ
    -0.19
    èıģ
    -0.18
     Hunger
    -0.18
    ç¢İ
    -0.18
    å©ļ纱
    -0.18
     Äijò
    -0.18
    POSITIVE LOGITS
    æĦŁåĨĴ
    0.27
    åĴ³åĹ½
    0.23
    æĬµæĬĹåĬĽ
    0.22
    ãĤ·ãĥ¼ãĤºãĥ³
    0.22
    åŃ£èĬĤ
    0.21
    è¢Ń
    0.21
    天æ°Ķ
    0.21
    æµģæĦŁ
    0.21
    ç§ĭåĨ¬
    0.21
    åij¼åIJ¸éģĵ
    0.21
    Activations Density 0.071%

    No Known Activations