© 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. 35406
    Prev
    Next
    INDEX
    Explanations

    software and tools

    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
     Ñģли
    -0.09
    åĪĽå»ºå·¥ä½ľ
    -0.09
    带头人
    -0.09
    ç«ł
    -0.09
    çIJĨäºĭä¼ļ
    -0.08
    çłĶ
    -0.08
     мн
    -0.08
    atsu
    -0.08
    è´£ç¼ĸ
    -0.08
    寿
    -0.08
    POSITIVE LOGITS
    软件
    0.13
     software
    0.11
    æĺ¯ä¸Ģ款
    0.11
    åħ®
    0.11
    è»Łé«Ķ
    0.11
    æĸ¯åŁº
    0.10
    è»Ł
    0.10
    ãĤ½ãĥķãĥĪ
    0.09
    msp
    0.09
    åĩºèī²çļĦ
    0.09
    Activations Density 0.078%

    No Known Activations