© 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. 2991
    Prev
    Next
    INDEX
    Explanations

    sepsis, bloodstream, systemic infections, shock

    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
     amort
    -0.27
     pronunciation
    -0.25
     rent
    -0.24
    è¾Ī
    -0.24
    åľ°å½¢
    -0.23
     apprent
    -0.23
    _rent
    -0.23
    åĿļ硬
    -0.23
     rents
    -0.22
     placements
    -0.22
    POSITIVE LOGITS
    åħ¨èº«
    0.30
    管ç½ij
    0.28
     bloodstream
    0.27
    è§ŀ
    0.26
    躯
    0.25
    æĢ§çĸ¾çĹħ
    0.25
    ä¸Ģ身
    0.25
     systemic
    0.25
    communic
    0.24
    åĽĽèĤ¢
    0.24
    Activations Density 0.107%

    No Known Activations