© 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. 2194
    Prev
    Next
    INDEX
    Explanations

    bonus, warning, hint, answer, alert, flash, disclaimer

    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
    éĶ²
    -0.10
    åıĺäºĨ
    -0.09
    éĿ¢åŃIJ
    -0.09
    念头
    -0.09
    导读
    -0.08
    è¿Ļä¸Ģ次
    -0.08
    大çĽĺ
    -0.08
     chuyá»ĩn
    -0.08
    ">ÃĹ</
    -0.08
    ä¸ºæł¸å¿ĥçļĦ
    -0.08
    POSITIVE LOGITS
    ically
    0.09
    åģĩæĹ¥
    0.09
     gerne
    0.08
    æ·¼
    0.08
     secret
    0.08
    /API
    0.08
    _ipc
    0.08
    ÙĬص
    0.08
    æĭĬ
    0.08
    atically
    0.08
    Activations Density 0.035%

    No Known Activations