© 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. 63139
    Prev
    Next
    INDEX
    Explanations

    oceanographic, geographic, climatic

    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
    éŸ
    -0.11
    å¾Īä¹ħ
    -0.11
    nect
    -0.10
    æĭĶ
    -0.10
    ruc
    -0.10
    ç¼ļ
    -0.09
    ìĦ¼
    -0.09
    ä¸Ģ声
    -0.09
    ÑĬ
    -0.09
    ÑĪив
    -0.09
    POSITIVE LOGITS
    ئ
    0.10
     Sanford
    0.10
    igkeit
    0.08
    s
    0.08
    æĢ»èĢĮè¨Ģä¹ĭ
    0.08
    à¤ĵ
    0.08
    è¢Ī
    0.08
    äºĶæĺŁ
    0.08
    èĩªåĪ¶
    0.07
    ä¸įåĨį
    0.07
    Activations Density 0.028%

    No Known Activations