© 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. 2853
    Prev
    Next
    INDEX
    Explanations

    genetic modification, transgenic

    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
    ä¸Ģå¥Ĺ
    -0.10
    -www
    -0.09
     Barb
    -0.09
    åİļéĩį
    -0.09
    å«ĸ
    -0.09
    ernes
    -0.08
    æ¸ħé¦Ļ
    -0.08
    å«Ķ
    -0.08
     unus
    -0.08
    åĬŀ好
    -0.08
    POSITIVE LOGITS
    ãģĭãģ©ãģĨãģĭ
    0.10
    è½¬åŁºåĽł
    0.09
    æ¤į
    0.09
     Monsanto
    0.09
    ä¿¡æģ¯åħ¬å¼Ģ
    0.08
    信念
    0.08
    å±ī
    0.08
    æijĬ
    0.08
    黯
    0.08
    TypeName
    0.08
    Activations Density 0.050%

    No Known Activations