© 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. 61889
    Prev
    Next
    INDEX
    Explanations

    majority of

    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
    æĽ´å¤ļä¿¡æģ¯
    -0.09
    å¤ļäºĨ
    -0.09
    arium
    -0.08
    太å¤ļ
    -0.08
    åīįæīĢ
    -0.08
    abled
    -0.08
    omics
    -0.08
    à¸Ľà¸£à¸²à¸ģà¸ı
    -0.08
     Jens
    -0.08
    æĽ´å¤ļ
    -0.08
    POSITIVE LOGITS
    æĥħåĨµä¸ĭ
    0.13
    è¿ĺæĺ¯è¦ģ
    0.11
    mente
    0.10
    ä¹ĥèĩ³
    0.10
    unch
    0.09
    çľģ份
    0.09
    æŶéĹ´åĨħ
    0.09
    OfWork
    0.09
    ä¹ĭä½ľ
    0.09
    onna
    0.09
    Activations Density 0.021%

    No Known Activations