© 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. 16819
    Prev
    Next
    INDEX
    Explanations

    end of war, surrender

    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
    åīĬ
    -0.10
    纶
    -0.10
    æĭĶ
    -0.09
    丼
    -0.09
    æĸ¥
    -0.09
    æİł
    -0.09
    ite
    -0.09
    åīįç½®
    -0.09
    lash
    -0.09
    è°ĭ
    -0.08
    POSITIVE LOGITS
    æĬķéĻį
    0.15
     surrender
    0.13
     Surre
    0.11
     capit
    0.11
     surre
    0.10
    ç»Ī
    0.10
     surrendered
    0.09
     deflate
    0.09
     submission
    0.09
    .reflect
    0.08
    Activations Density 0.042%

    No Known Activations