© 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. 54419
    Prev
    Next
    INDEX
    Explanations

    author description

    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
    éľĨ
    -0.08
    è¿Ļä¸Ģ次
    -0.08
    大佬
    -0.08
    åĪ°æľĢåIJİ
    -0.08
    è¿Ļæĸ¹éĿ¢
    -0.08
    ä¸Ģä¸ĭ
    -0.08
    å¿®
    -0.08
    theless
    -0.08
    ä¸¥æł¼æĮīçħ§
    -0.08
    è¿Ļæł·ä¸Ģ
    -0.08
    POSITIVE LOGITS
    åĨĻä½ľ
    0.10
    ãĢĤwww
    0.10
     içerik
    0.09
    dzi
    0.09
    PLL
    0.09
    åĨĻäºĨ
    0.09
    .Author
    0.08
     Writers
    0.08
    bsite
    0.08
    eon
    0.08
    Activations Density 0.155%

    No Known Activations