© 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. 29678
    Prev
    Next
    INDEX
    Explanations

    participated, dominated, directed

    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
    èĩ£
    -0.10
    pling
    -0.09
    æIJª
    -0.09
     Jog
    -0.09
    ibel
    -0.09
    ooks
    -0.09
    è¿ĺ好
    -0.08
    ãģĹãģ¦ãģĬãģı
    -0.08
    éĤ®å¯Ħ
    -0.08
    chas
    -0.08
    POSITIVE LOGITS
    rog
    0.09
    ube
    0.09
    为代表
    0.09
    æĺ¯ä¸Ģ座
    0.08
    å¤ĩ
    0.08
     Kay
    0.08
     Ire
    0.08
    æIJ¬å®¶
    0.08
    rop
    0.08
    èĹ»
    0.08
    Activations Density 0.005%

    No Known Activations