© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20330
    Prev
    Next
    INDEX
    Explanations

    award ceremonies

    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
    çģĮ
    -0.10
    åŃĢ
    -0.09
    丧
    -0.09
    INGS
    -0.09
    åĺĽ
    -0.09
    زÙĦ
    -0.09
    akra
    -0.09
     qual
    -0.09
    跻身
    -0.09
    éĵİ
    -0.09
    POSITIVE LOGITS
    ä»ĭç»įäºĨ
    0.09
    举起
    0.09
     Redistribution
    0.09
    ecom
    0.09
    èĩ´è¾ŀ
    0.08
    主æĮģ
    0.08
    æļ§
    0.08
     cord
    0.08
    èµ·åĪĿ
    0.08
    佩æĪ´
    0.08
    Activations Density 0.047%

    No Known Activations