© 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. 2010
    Prev
    Next
    INDEX
    Explanations

    Jesus Christ and America

    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
    碲
    -0.10
    éĴ¿
    -0.10
    éºĭ
    -0.10
    ires
    -0.09
    ä¸Ģ对
    -0.09
    æĺİçıł
    -0.09
    çįŃ
    -0.09
    wnd
    -0.09
    osite
    -0.09
    æĹ¶ä»£ä¸ŃåĽ½
    -0.09
    POSITIVE LOGITS
    åİŁæłĩé¢ĺ
    0.10
    è¦ģç´§
    0.08
     ih
    0.08
    羣å®ŀçļĦ
    0.08
    ä¼ļä¸įä¼ļ
    0.08
    ham
    0.08
    ĥĿ
    0.08
    dens
    0.08
    0.08
    以åıĬ
    0.08
    Activations Density 0.026%

    No Known Activations