© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 729
    Prev
    Next
    INDEX
    Explanations

    work and commute

    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
    Negative Logits
    ç»ķ
    -0.09
    ä¼łçľŁ
    -0.09
    éĵ¿
    -0.09
    æīŃ
    -0.08
    æıĸ
    -0.08
    两天
    -0.08
    ulp
    -0.08
    ç¹ŀ
    -0.08
    çķĻå®ĪåĦ¿ç«¥
    -0.08
    çīµå¼ķ
    -0.08
    POSITIVE LOGITS
    ä¸ĬçıŃ
    0.11
    èĩ³ä¸Ĭ
    0.10
    çīŁ
    0.09
    ä¸ĬçıŃæĹı
    0.09
    ä¸ĬåѦ
    0.09
    çIJĨæĻº
    0.09
    æ¯ı次éĥ½
    0.09
    åĩºè¡Į
    0.09
    hil
    0.09
    åĪļéľĢ
    0.09
    Activations Density 0.029%

    No Known Activations