© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8956
    Prev
    Next
    INDEX
    Explanations

    network regions and servers

    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
    鬼
    -0.10
    迷人
    -0.10
    è¾ĵç»Ļ
    -0.09
    วà¸Ķ
    -0.09
    è¿·
    -0.09
    uries
    -0.09
    åĹ·
    -0.09
    /browse
    -0.09
    æµģåĬ¨
    -0.09
     transf
    -0.09
    POSITIVE LOGITS
    å¦ĤæĦı
    0.09
    çĪĨ
    0.09
    æĮŁ
    0.09
    æĿİåħĪçĶŁ
    0.09
     Buster
    0.09
    enh
    0.08
    CN
    0.08
     PC
    0.08
    诱
    0.08
    ä¼ĺç§ĢçļĦ
    0.08
    Activations Density 0.104%

    No Known Activations