© 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. 6122
    Prev
    Next
    INDEX
    Explanations

    gut microbiota and probiotics

    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
    .maximum
    -0.09
    bru
    -0.09
    追踪
    -0.09
    prefer
    -0.09
    tab
    -0.09
    触
    -0.09
    æĬķ注
    -0.09
    æ²ī
    -0.09
     prefer
    -0.08
    _tab
    -0.08
    POSITIVE LOGITS
    åŀĵ
    0.09
    èĤłéģĵ
    0.09
     gut
    0.09
    åłij
    0.09
    èıĮ
    0.08
    ãĥįãĤ¿
    0.08
    .uni
    0.08
    麸
    0.08
    _logging
    0.08
     prob
    0.08
    Activations Density 0.084%

    No Known Activations