© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2867
    Prev
    Next
    INDEX
    Explanations

    suspected illness diagnosis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
     skirts
    -0.25
     fences
    -0.25
    åIJĮæĦı
    -0.25
     bottoms
    -0.24
    è·¯ç¨ĭ
    -0.23
    æĶ»
    -0.23
    æĹģ
    -0.23
    åİŁæľ¬
    -0.22
    åĪĨæĺİ
    -0.22
    æī©å»º
    -0.22
    POSITIVE LOGITS
     diagnosis
    0.26
    æĤ£çĹħ
    0.25
    æĤ£ä¸Ĭ
    0.24
    æĤ£èĢħ
    0.23
    以èĩ´
    0.23
    ä¹Łå¥½
    0.23
     illness
    0.23
     Pregn
    0.23
    æľīä»»ä½ķ
    0.23
     Injury
    0.23
    Activations Density 0.005%

    No Known Activations