© 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. 22046
    Prev
    Next
    INDEX
    Explanations

    Christians / Christian faith

    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
    æ´ĭæ´ĭ
    -0.10
    æĦŁè§¦
    -0.10
    æĶ¯éħį
    -0.10
    éķ¿ä¸īè§Ĵ
    -0.09
    è§Ĥåħī
    -0.09
    è§Ĩå¯Ł
    -0.09
    å¤įåħ´
    -0.09
    建åįİ
    -0.09
    èĬ±åĽŃ
    -0.09
    è°ĥéħį
    -0.09
    POSITIVE LOGITS
    çĶŁæ´»æ°´å¹³
    0.09
    ocking
    0.09
    ADER
    0.09
     Huff
    0.09
    tracts
    0.09
    éķĬ
    0.09
    åħ±åIJĮä½ĵ
    0.09
    VEC
    0.09
    æªĢ
    0.09
    Anywhere
    0.09
    Activations Density 0.049%

    No Known Activations