© 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. 48423
    Prev
    Next
    INDEX
    Explanations

    modern times

    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
    好çľĭçļĦ
    -0.09
    飫
    -0.09
    åį¯
    -0.08
    åİŁæľīçļĦ
    -0.08
    æľĪä¸Ń
    -0.08
    ëģ¼
    -0.08
    ä¼ģä¸ļ管çIJĨ
    -0.08
    è¿ĽèĢĮ
    -0.08
    ivar
    -0.08
    æĹ©
    -0.08
    POSITIVE LOGITS
    çݰ代
    0.17
    çİ°åľ¨çļĦ
    0.17
    ä»Ĭ天çļĦ
    0.16
     modern
    0.15
    å½ĵä»Ĭ
    0.15
    æĸ°ä¸Ģ代
    0.15
     today
    0.15
    çİ°ä»Ĭ
    0.15
    ä»Ĭ天
    0.15
    modern
    0.14
    Activations Density 0.197%

    No Known Activations