© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40053
    Prev
    Next
    INDEX
    Explanations

    church and religious buildings

    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
    åĨĹ
    -0.10
    饶
    -0.10
    çķĻç»Ļ
    -0.09
    æ§Ł
    -0.09
    éģĤ
    -0.09
    éĶ´
    -0.09
    å½Ģ
    -0.09
    éģĴ
    -0.09
     prefect
    -0.08
    _DISPATCH
    -0.08
    POSITIVE LOGITS
    æķĻåłĤ
    0.10
    ä¿¡ä»°
    0.09
     attendance
    0.09
     attending
    0.09
    tem
    0.09
    寺åºĻ
    0.09
    boro
    0.09
    Built
    0.08
    åįıä¼ļ
    0.08
    åŁºçĿ£æķĻ
    0.08
    Activations Density 0.145%

    No Known Activations