© 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. 55025
    Prev
    Next
    INDEX
    Explanations

    French administrative divisions

    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
    pur
    -0.09
    ðŁĵĮ
    -0.09
     Pur
    -0.09
    /gui
    -0.08
    没
    -0.08
    æĺİæľĿ
    -0.08
    åĽ´
    -0.08
    rove
    -0.08
    御
    -0.08
    à¹Ģà¸Ī
    -0.08
    POSITIVE LOGITS
    æķ´é½IJ
    0.11
    æľīäºĽäºº
    0.10
    å°ıé¢Ŀ贷款
    0.10
    åijĹ
    0.09
    æľºåŀĭ
    0.09
    herited
    0.09
    keh
    0.09
    kek
    0.09
    åĩ¶
    0.09
    论
    0.09
    Activations Density 0.133%

    No Known Activations