© 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. 9011
    Prev
    Next
    INDEX
    Explanations

    animals and living things

    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
    æ¶ĵ
    -0.10
    çĭ®åŃIJ
    -0.10
    鲨
    -0.09
    èİĨ
    -0.09
    inalg
    -0.09
     lions
    -0.09
    reon
    -0.09
    ç²Ĺ
    -0.09
    ç²®
    -0.08
    dragon
    -0.08
    POSITIVE LOGITS
     McGr
    0.09
    kir
    0.09
    åIJĮç±»
    0.09
     kir
    0.08
    åĩĢ
    0.08
    ä¼Ļ
    0.08
    éļĪ
    0.08
    çļĦå°ı
    0.08
     HERO
    0.08
    ynchronized
    0.08
    Activations Density 0.269%

    No Known Activations