© 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. 1088
    Prev
    Next
    INDEX
    Explanations

    secular vs religious beliefs

    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
    ä¿Ŀå®Ī
    -0.12
     conservatism
    -0.12
    éĴĵ
    -0.12
     conservative
    -0.11
    vé
    -0.10
     Conservative
    -0.10
    æŃ£å½ĵ
    -0.09
     conservatives
    -0.09
    å´ĩé«ĺ
    -0.09
    ä¸ĢåĪĢ
    -0.09
    POSITIVE LOGITS
    æ·¡åĮĸ
    0.13
     secular
    0.10
    ä¸įåĨį
    0.10
    ä¸ĸä¿Ĺ
    0.10
    åīĬå¼±
    0.10
    èĦ±èIJ½
    0.10
    è´¨çĸij
    0.09
    çݰ代社ä¼ļ
    0.09
    å¤ļåħĥ
    0.09
    太åŃIJ
    0.09
    Activations Density 0.227%

    No Known Activations