© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20002
    Prev
    Next
    INDEX
    Explanations

    legal judgments and decisions

    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
    èī¯å¥½çļĦ
    -0.10
    è¾Ļ
    -0.10
    osen
    -0.09
    裾
    -0.09
    inia
    -0.08
    éĢ¢
    -0.08
    çľ¼çľĭ
    -0.08
    æľķ
    -0.08
    èĨı
    -0.08
    åħīèį£
    -0.08
    POSITIVE LOGITS
    æĬ±
    0.10
    ç½ijç«Ļ建设
    0.10
    çĶ¨å¾®ä¿¡
    0.10
    ycop
    0.09
    çĹħåĽł
    0.08
    ãĤµãĤ¤ãĥĪ
    0.08
    åīįç½®
    0.08
    ä¸Ģè§Ĵ
    0.08
     Bundy
    0.08
     spar
    0.08
    Activations Density 0.054%

    No Known Activations