© 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. 34069
    Prev
    Next
    INDEX
    Explanations

    Roman Catholic clergy and titles

    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
    .cy
    -0.10
    å·Ŀ
    -0.08
    çĪ·
    -0.08
     Cy
    -0.08
    ç¦ıå¾·
    -0.08
    大éĿ¢ç§¯
    -0.08
    æĹłæĥħ
    -0.08
    te
    -0.07
    åIJĬ
    -0.07
    åºĻ
    -0.07
    POSITIVE LOGITS
    Disappear
    0.10
     Kitt
    0.10
    âĸ¾
    0.09
    .AppSettings
    0.09
    xmm
    0.09
    åħľ
    0.09
    Äĥn
    0.09
    -publish
    0.09
    ÑıÑĤиÑı
    0.09
    ç¨Ķ
    0.09
    Activations Density 0.064%

    No Known Activations