© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 11062
    Prev
    Next
    INDEX
    Explanations

    academic presentations and meetings

    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
    лей
    -0.10
    è·³
    -0.09
     phẩm
    -0.09
    åĬłä»¥
    -0.09
    ç±Ģ
    -0.08
     lat
    -0.08
     INST
    -0.08
    lat
    -0.08
    æłī
    -0.08
    è·¨çķĮ
    -0.08
    POSITIVE LOGITS
    çłĶ究æĪIJæŀľ
    0.12
    ä¸ĢåĪĻ
    0.11
    ä¼ļè®®ä¸Ĭ
    0.10
     trình
    0.10
    大ä¼ļä¸Ĭ
    0.10
    æĪIJæŀľ
    0.10
    oir
    0.09
     presentation
    0.09
    åŃ¦æľ¯
    0.09
    书éĿ¢
    0.09
    Activations Density 0.136%

    No Known Activations