© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1196
    Prev
    Next
    INDEX
    Explanations

    neonatal, maternal, congenital transmission

    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
    æī¿æĭħ责任
    -0.23
    æ°¾
    -0.23
     NotImplemented
    -0.23
    æĥķ
    -0.23
     metab
    -0.23
    æļ§æĺ§
    -0.23
    insky
    -0.22
    åIJĦå¼ı
    -0.22
    åģ¥èº«
    -0.22
     Flood
    -0.22
    POSITIVE LOGITS
    ä¼łè¾ĵ
    0.28
    æ¸ĹéĢı
    0.28
    transfer
    0.26
    转移åĪ°
    0.26
    æ®ĭçķĻ
    0.26
    Transfer
    0.25
    çªģåĽ´
    0.24
    æľª
    0.24
    é¢ĦçķĻ
    0.23
    转移
    0.23
    Activations Density 0.028%

    No Known Activations