© 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. 60661
    Prev
    Next
    INDEX
    Explanations

    organization activities

    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
    æľ¬ç½ij
    -0.11
    æĺ¯ä¸ĢåIJį
    -0.09
    æĸ°éĹ»è®°èĢħ
    -0.09
    为å¥ijæľº
    -0.09
    æĤŁ
    -0.08
    æŦ
    -0.08
    shares
    -0.08
     baptized
    -0.08
    åıĸèĥľ
    -0.08
    share
    -0.08
    POSITIVE LOGITS
    æĪIJç«ĭäºİ
    0.13
    ç»Ħç»ĩå®ŀæĸ½
    0.12
    å®ĹæŨ
    0.12
    èĩ´åĬĽäºİ
    0.11
    æľºæŀĦ
    0.11
    oundation
    0.11
    ç»Ħç»ĩ
    0.11
    æĪIJç«ĭ以æĿ¥
    0.11
    ç«łç¨ĭ
    0.10
    æĢ»éĥ¨
    0.10
    Activations Density 0.145%

    No Known Activations