© 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. 488
    Prev
    Next
    INDEX
    Explanations

    divine and religious figures

    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
    ä¸Ģ群人
    -0.24
    èijĽ
    -0.23
    身价
    -0.23
    çŀł
    -0.23
    è¿Ļæī¹
    -0.23
    ä¸ĢéŨ
    -0.23
    ä¸Ģ个èģĮä¸ļ
    -0.22
     Compound
    -0.22
     Live
    -0.22
     archives
    -0.22
    POSITIVE LOGITS
    ä¸Ĭå¸Ŀ
    0.37
     God
    0.34
     سبØŃاÙĨÙĩ
    0.34
     divine
    0.33
    God
    0.33
     provid
    0.32
    èµIJ
    0.29
     Allah
    0.29
     Ðijог
    0.28
     Almighty
    0.28
    Activations Density 0.081%

    No Known Activations