© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50957
    Prev
    Next
    INDEX
    Explanations

    Christian beliefs and teachings

    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
    oga
    -0.09
    aleb
    -0.08
     flipping
    -0.08
    ç¿»
    -0.08
     Libert
    -0.08
    æĸ°åŀĭåĨłçĬ¶
    -0.08
     sickness
    -0.08
    atic
    -0.07
    åĵij
    -0.07
    levance
    -0.07
    POSITIVE LOGITS
    åĪĨæł¡
    0.11
    æĸ°éĻĪ代谢
    0.10
    欧å¼ı
    0.09
    ä¼łç»Ł
    0.09
    éĴĹ
    0.09
    åĤ³çµ±
    0.09
    ä¼łç»ŁçļĦ
    0.09
    å¿Ŀ
    0.09
     Monsters
    0.09
    宣称
    0.09
    Activations Density 0.106%

    No Known Activations