© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52232
    Prev
    Next
    INDEX
    Explanations

    sell your copies

    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
    æį¢äºĨ
    -0.10
    æĢ§å¼º
    -0.09
    æĸ¹å¼ıè¿Ľè¡Į
    -0.09
    ç½²
    -0.09
    Nested
    -0.08
    ä¸Ģ头
    -0.08
    nested
    -0.08
    ilio
    -0.08
    earch
    -0.08
    æī®
    -0.08
    POSITIVE LOGITS
    _RG
    0.09
    Pont
    0.09
    æĮĩæłĩ
    0.09
    çłŃ
    0.09
    黾
    0.08
    à¹ģà¸ľà¸Ļ
    0.08
    以åħ¶
    0.08
    æ¯ĸ
    0.08
    æĤ¯
    0.08
    æĥķ
    0.08
    Activations Density 0.005%

    No Known Activations