© 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. 62062
    Prev
    Next
    INDEX
    Explanations

    oil pump or terminal

    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
    å¡ŀ
    -0.11
    æ¼Ĥ
    -0.10
    æĶĢ
    -0.09
    å¸Ń
    -0.09
    奢ä¾Īåĵģ
    -0.09
    ç©¿æ¢Ń
    -0.09
    éĢĹ
    -0.09
    æĿµ
    -0.08
    itat
    -0.08
    å¼¥
    -0.08
    POSITIVE LOGITS
    åĩī
    0.10
    STA
    0.10
     Pens
    0.09
     zij
    0.09
     ÑĤеÑħнолог
    0.09
    æıIJæĭĶ
    0.09
    (handles
    0.09
    èIJ¥ä¸ļé¢Ŀ
    0.09
     tones
    0.09
    欢åĸľ
    0.08
    Activations Density 0.095%

    No Known Activations