© 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. 47885
    Prev
    Next
    INDEX
    Explanations

    fixed charge or sum

    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
    æĿĪ
    -0.09
    /widget
    -0.09
    ä¸¥æł¼æī§è¡Į
    -0.09
    å®ŀæŶ
    -0.08
     Mé
    -0.08
     Erik
    -0.08
    导åIJij
    -0.08
    Aware
    -0.08
    åĸĺ
    -0.08
     Kant
    -0.08
    POSITIVE LOGITS
    ä¸į管
    0.12
    ä¸įåıĺ
    0.10
    æĹłè®º
    0.10
    åĽ¢
    0.09
    åĩºåİĤ
    0.09
    ä¸į论
    0.09
    åĩ¡
    0.09
    åĽºå®ļ
    0.08
     garage
    0.08
    æĹı
    0.08
    Activations Density 0.035%

    No Known Activations