© 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. 16725
    Prev
    Next
    INDEX
    Explanations

    made up their mind

    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
    .Sdk
    -0.10
    符
    -0.09
     Hague
    -0.09
    igans
    -0.09
    YTE
    -0.08
    åѦä¼ļ
    -0.08
    æľīä»·åĢ¼
    -0.08
    å°İ
    -0.08
    æ¯Ķéĩį
    -0.08
    åīįæīĢæľª
    -0.08
    POSITIVE LOGITS
    åĽºå®ļ
    0.16
    å®ļäºĨ
    0.15
    fixed
    0.15
    åĨ³å®ļ
    0.14
     fixed
    0.14
    åĨ³å®ļäºĨ
    0.13
    決å®ļ
    0.13
    åĽºå®ļçļĦ
    0.13
    -fixed
    0.13
    å®ļ
    0.13
    Activations Density 0.068%

    No Known Activations