© 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. 26282
    Prev
    Next
    INDEX
    Explanations

    microbial degradation and bioremediation

    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
    åijĹ
    -0.09
    ç¿Į
    -0.09
    èĥ´
    -0.08
    ä»ĵåºĵ
    -0.08
    éĢĢåĩº
    -0.08
    æ»ij
    -0.08
    æ¸ħæĻ¨
    -0.08
    赤
    -0.08
    滥
    -0.08
    庵
    -0.08
    POSITIVE LOGITS
    æĭħ
    0.10
     từng
    0.10
    åĬ©
    0.09
    éĻį
    0.09
    æĩĤäºĭ
    0.09
     çıkar
    0.09
    маÑĢ
    0.09
    ä¸į认è¯Ĩ
    0.09
    æī¿æĭħ
    0.09
    ä»ĭåħ¥
    0.09
    Activations Density 0.229%

    No Known Activations