© 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. 51938
    Prev
    Next
    INDEX
    Explanations

    doing something

    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
    æĺķ
    -0.09
    æĪij以为
    -0.08
     thiá»ĩt
    -0.08
    æĬĬèĩªå·±çļĦ
    -0.08
    æĪij们ä¼ļ
    -0.08
    oose
    -0.08
    ä½ĵ系建设
    -0.08
    çŃī人
    -0.08
    inne
    -0.08
    uest
    -0.08
    POSITIVE LOGITS
    æĪIJåĬŁ
    0.11
    ãģĵãģ¨ãģĮãģ§ãģįãĤĭ
    0.11
    ä¸ĵ线
    0.10
    ä½ĵä¼ļåĪ°
    0.10
    èĥ½å¾ĹåĪ°
    0.10
    ables
    0.10
    æĪIJåĬŁçļĦ
    0.10
    ãģĵãģ¨ãģĮãģ§ãģį
    0.09
     Successfully
    0.09
    åħ¨æł¡
    0.09
    Activations Density 0.617%

    No Known Activations