© 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. 5544
    Prev
    Next
    INDEX
    Explanations

    just the beginning

    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
    alternate
    -0.09
    é¢ijéģĵ
    -0.09
     Previous
    -0.08
    æŶæŶ
    -0.08
    ä¸Ģ声
    -0.08
    à¦Ļ
    -0.08
    æľĢåĸľæ¬¢çļĦ
    -0.08
    çī¹æľīçļĦ
    -0.08
    ä¸įåIJĮäºİ
    -0.08
    uv
    -0.08
    POSITIVE LOGITS
    åºıå¹ķ
    0.13
    åĪļå¼Ģå§ĭ
    0.12
    åıªæĺ¯ä¸Ģ个
    0.12
    éĺ¶æ®µ
    0.12
    è¿Ļåıªæĺ¯
    0.11
    å¼Ģ端
    0.11
    èµ·æŃ¥
    0.11
    å¼Ģå±Ģ
    0.10
    æĸ°ç¯ĩç«ł
    0.09
    å¼Ģå§ĭ
    0.09
    Activations Density 0.019%

    No Known Activations