© 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. 47658
    Prev
    Next
    INDEX
    Explanations

    save game states

    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¥ŀç§ĺ
    -0.10
     VE
    -0.10
    .ta
    -0.10
    oday
    -0.09
    ç«Ļéķ¿
    -0.09
    è°ģçŁ¥éģĵ
    -0.09
    -pagination
    -0.09
    å°¤åħ¶
    -0.09
    ä¸İä¼Ĺ
    -0.08
    æ½®
    -0.08
    POSITIVE LOGITS
    æĬķèµĦåŁºéĩij
    0.10
    ä¼ij
    0.09
    åĬŀäºĭ
    0.09
    沮丧
    0.09
    é£Ĵ
    0.09
    æĶ¾åѦ
    0.09
    çģŃ
    0.09
    çij
    0.08
    æ¾ľ
    0.08
    æĶ¾ç½®
    0.08
    Activations Density 0.053%

    No Known Activations