© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36961
    Prev
    Next
    INDEX
    Explanations

    histamine, sleep, medications

    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
    ç²īç¢İ
    -0.11
    ä¸Ģä½ĵ
    -0.10
    çļĪ
    -0.10
    ward
    -0.09
    unte
    -0.09
    åĭŁéĽĨèµĦéĩij
    -0.09
    spl
    -0.09
    å¼Ł
    -0.09
    å¡ijèĥ¶
    -0.09
     fantas
    -0.09
    POSITIVE LOGITS
     sleepy
    0.12
     tired
    0.11
    åĽ°
    0.11
    çĸ²åĬ³
    0.09
    æĥº
    0.09
    aise
    0.08
    å̦
    0.08
     sleep
    0.08
    ä¹ı
    0.08
    æĬ¼
    0.08
    Activations Density 0.087%

    No Known Activations