© 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. 22458
    Prev
    Next
    INDEX
    Explanations

    religious texts and scripture

    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
    inn
    -0.09
    æľīæľº
    -0.08
    æħİ
    -0.08
    iegel
    -0.08
     essay
    -0.08
    åIJĥ
    -0.08
    å¿ĥä¸Ń
    -0.08
     SCR
    -0.08
    é«ĺå°ļ
    -0.08
    身份
    -0.08
    POSITIVE LOGITS
    éŁ
    0.10
    马æĭī
    0.10
    oun
    0.10
    ç»ıéĶĢ
    0.10
    大声
    0.09
    æŃ£åĵģ
    0.09
    åľ£
    0.09
     влад
    0.09
    èģĸ
    0.09
    飵
    0.09
    Activations Density 0.055%

    No Known Activations