© 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. 18876
    Prev
    Next
    INDEX
    Explanations

    clock hours or day parts

    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
    èĬ¸
    -0.09
    opi
    -0.09
    åįĥéĩĮ
    -0.09
    ä»ĬæĻļ
    -0.09
    ç¿ħ
    -0.09
    å¯Ħ
    -0.09
     stad
    -0.09
    Ø´Ùģ
    -0.09
    æĻļé¤IJ
    -0.09
    æĻļ
    -0.08
    POSITIVE LOGITS
    çĸĶ
    0.10
     ros
    0.10
    ä¸įåĪĨ
    0.10
     merry
    0.09
    ä¸įèĪį
    0.09
    olest
    0.09
    æ»ļæ»ļ
    0.09
    ä¸įå¿ĺ
    0.08
    åįĬ个
    0.08
    çĸĸ
    0.08
    Activations Density 0.010%

    No Known Activations