© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22461
    Prev
    Next
    INDEX
    Explanations

    God and religion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    大éĿ¢ç§¯
    -0.09
    моÑĤ
    -0.08
    æĮ¨
    -0.08
    à¸Ĺร
    -0.08
    æĢĿè·¯
    -0.08
    äºĮ人
    -0.08
    çIJµ
    -0.08
    æĥ³
    -0.08
     enc
    -0.08
    1
    -0.08
    POSITIVE LOGITS
    ä¸Ĭå¸Ŀ
    0.14
    otch
    0.11
     God
    0.10
    God
    0.10
    çľĭä¸įè§ģ
    0.10
    éļIJå½¢
    0.09
    æ±ĤåĬ©
    0.09
    éĵ¤
    0.09
    religious
    0.09
    chten
    0.09
    Activations Density 0.060%

    No Known Activations