© 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. 40391
    Prev
    Next
    INDEX
    Explanations

    bacterial infections and pathogens

    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
    ãģ£ãģįãĤĬ
    -0.11
    croll
    -0.10
    mist
    -0.09
    ê°Ŀ
    -0.09
    oram
    -0.08
    edor
    -0.08
    obar
    -0.08
    edi
    -0.08
    æīĵåĩ»
    -0.08
    inar
    -0.08
    POSITIVE LOGITS
    emia
    0.11
    åIJĮå¿Ĺ们
    0.10
    icide
    0.10
    emento
    0.09
    ally
    0.09
    çİĭåĽ½
    0.09
    urre
    0.09
    -filled
    0.09
    说æĺ¯
    0.08
    åħ³éŨ
    0.08
    Activations Density 0.074%

    No Known Activations