© 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. 20923
    Prev
    Next
    INDEX
    Explanations

    theater or theatre

    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
       
    -0.11
    åĩºåİĤ
    -0.09
    ä¸įäºĨ
    -0.09
    禺
    -0.09
    ãģĵãģ¨ãģĮå¤ļãģĦ
    -0.09
    ãģ£ãģĵ
    -0.09
    sert
    -0.09
    ع
    -0.09
    éķ¿éĢĶ
    -0.09
    itude
    -0.08
    POSITIVE LOGITS
    oretical
    0.10
    ellers
    0.10
    UNCH
    0.10
    åĨħçļĦ
    0.09
    éĩĮçļĦ
    0.09
    ä¸Ģå¹ķ
    0.09
    letes
    0.09
    ackle
    0.09
    eing
    0.09
    ically
    0.09
    Activations Density 0.015%

    No Known Activations