© 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. 13890
    Prev
    Next
    INDEX
    Explanations

    drug resistance

    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
     ambigu
    -0.20
     Ying
    -0.20
    éĢĤå½ĵçļĦ
    -0.18
    ä»£æĽ¿
    -0.18
    iets
    -0.18
    æĶĴ
    -0.18
    ospace
    -0.18
    主ä½ĵ
    -0.18
     zam
    -0.18
     tack
    -0.18
    POSITIVE LOGITS
     resistance
    0.24
     attempts
    0.23
     Resistance
    0.22
    weis
    0.20
    ethnic
    0.20
    æ±Ĺæ°´
    0.19
    失æķĪ
    0.19
    Resistance
    0.19
    æĹłæķĪ
    0.19
    ä¼ģ
    0.18
    Activations Density 0.266%

    No Known Activations