© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21617
    Prev
    Next
    INDEX
    Explanations

    Germany and German entities

    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
    æĸ°å¼Ģ
    -0.11
    ç½ijéĢļ
    -0.10
    çµ®
    -0.09
    éĶ¦æłĩ
    -0.09
    æī
    -0.09
    åij
    -0.09
    æľ¬äºº
    -0.09
    æŶ髦
    -0.08
    auer
    -0.08
    å¸ļ
    -0.08
    POSITIVE LOGITS
    å¾·åĽ½
    0.11
    ãĥīãĤ¤ãĥĦ
    0.10
     Germany
    0.09
    Germany
    0.09
    urd
    0.09
    羦
    0.09
    æ¡ĮéĿ¢
    0.09
     stall
    0.09
     German
    0.09
    ä½łçľĭ
    0.09
    Activations Density 0.064%

    No Known Activations