© 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. 59074
    Prev
    Next
    INDEX
    Explanations

    lung cancer

    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
    Not in Any Lists

    No Comments

    Negative Logits
    è²Į
    -0.09
    æħ¨
    -0.09
    é²ľæĺİ
    -0.09
    çĶµæ±ł
    -0.09
    ç°ª
    -0.09
    åłķ
    -0.09
    èĥ¯
    -0.09
    -exc
    -0.09
    éļıå¤Ħ
    -0.09
    壬
    -0.09
    POSITIVE LOGITS
    èĤº
    0.16
     lungs
    0.15
     lung
    0.14
    lung
    0.14
     Airways
    0.14
    éĻ¤å°ĺ
    0.14
     Lung
    0.14
    éĽ¾éľ¾
    0.14
    èĤºçĻĮ
    0.13
     Dust
    0.13
    Activations Density 0.374%

    No Known Activations