© 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. 28013
    Prev
    Next
    INDEX
    Explanations

    government and political staff

    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
    驾é©Ń
    -0.10
    ä¸įäºĨ
    -0.10
    å½ĵä¹ĭæĹłæĦ§
    -0.09
     branch
    -0.09
    åİĭåĪ¶
    -0.09
    åĪĨæĶ¯
    -0.08
     Harness
    -0.08
    åĭĩ士
    -0.08
    inte
    -0.08
    erten
    -0.08
    POSITIVE LOGITS
    åľĪ
    0.10
    æŀķ
    0.09
    æīİ
    0.09
    edd
    0.08
    antz
    0.08
    cce
    0.08
    æį®æĬ¥éģĵ
    0.08
    виз
    0.08
    èĢ¦
    0.08
    é¢Į
    0.08
    Activations Density 0.018%

    No Known Activations