© 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. 2189
    Prev
    Next
    INDEX
    Explanations

    crises and pandemic

    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
     Lafayette
    -0.26
    å¼ĢæľĹ
    -0.25
     Fees
    -0.24
     fees
    -0.24
     specialty
    -0.24
     staff
    -0.24
    åīįå¾Ģ
    -0.24
     pod
    -0.23
     taps
    -0.23
    æ½¢
    -0.23
    POSITIVE LOGITS
    -era
    0.33
    å°ı康社ä¼ļ
    0.31
    è¿Ļåľº
    0.30
    æĹ¶ä»£çļĦ
    0.29
    éĢłæĪIJçļĦ
    0.29
    åŀ®
    0.28
    æĹ¶ä»£
    0.28
    åıĬåħ¶ä»ĸ
    0.26
     hindsight
    0.26
    ä¸įç¡®å®ļæĢ§
    0.26
    Activations Density 0.084%

    No Known Activations