© 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. 980
    Prev
    Next
    INDEX
    Explanations

    ceremony or ritual context

    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
     rugged
    -0.28
    cheap
    -0.28
    æĭ¥æľī
    -0.27
    éķ¿æľŁ
    -0.27
     desperately
    -0.27
    æĬķèµĦ
    -0.27
    æĢ¨
    -0.27
     bulld
    -0.26
    engine
    -0.26
    plug
    -0.26
    POSITIVE LOGITS
    仪å¼ı
    0.38
     preceding
    0.34
     performed
    0.33
    ä¸ĢèĪ¬æĺ¯
    0.33
     optionally
    0.32
     ceremony
    0.32
     Ceremony
    0.32
    æľĹ诵
    0.32
    åĩĨå¤ĩå·¥ä½ľ
    0.32
     rhythm
    0.32
    Activations Density 0.026%

    No Known Activations