© 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. 16823
    Prev
    Next
    INDEX
    Explanations

    disinfecting and sterile conditions

    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
    emon
    -0.10
    èĩªçĦ¶ä¿ĿæĬ¤
    -0.09
    onné
    -0.09
    EMON
    -0.09
    éĺ´å½±
    -0.09
    ç©¿çĿĢ
    -0.09
    ç½®
    -0.09
     Boeh
    -0.09
     Affero
    -0.08
    oard
    -0.08
    POSITIVE LOGITS
     Hugo
    0.10
    xing
    0.09
    å¨Ĩ
    0.09
    éĿ¢åīį
    0.09
    izable
    0.08
    çĻĸ
    0.08
     Lunar
    0.08
    antis
    0.08
    çļĦç¨ĭ度
    0.08
    äºĨä»ĸçļĦ
    0.08
    Activations Density 0.026%

    No Known Activations