© 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. 9416
    Prev
    Next
    INDEX
    Explanations

    who followed by verb

    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
     اÙĦتÙĨ
    -0.11
    æĹħé¦Ĩ
    -0.10
    åĽłä¸ºä»ĸ们
    -0.10
    çĸĻ
    -0.09
    ictions
    -0.09
    è¾İ
    -0.09
    åIJĦæł·
    -0.09
    _RD
    -0.09
    éĻĦ件
    -0.09
    馥
    -0.09
    POSITIVE LOGITS
    ç¬ĶèĢħ
    0.08
     earlier
    0.08
    åݻ年
    0.08
    æĪijä»¬åľ¨
    0.08
     yesterday
    0.07
    æĹ¥åīį
    0.07
    ableView
    0.07
     пÑĢедÑģÑĤавлÑı
    0.07
     neut
    0.07
     incident
    0.07
    Activations Density 0.050%

    No Known Activations