© 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. 37507
    Prev
    Next
    INDEX
    Explanations

    discussing opportunities and strategies

    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
    ÙĩاÙħ
    -0.09
    å·´åŁº
    -0.09
    anke
    -0.09
    çªĿ
    -0.09
     Parr
    -0.09
    æĹłå£°
    -0.09
    éĵĸ
    -0.08
    èľ£
    -0.08
    enso
    -0.08
    æľīäºĨ
    -0.08
    POSITIVE LOGITS
    à¹ĥà¸Ļà¸ģาร
    0.11
    åħ³äºİ
    0.11
     regarding
    0.11
     for
    0.08
    æѤ类
    0.08
    åIJĦç±»
    0.08
     Gio
    0.08
    Ø·ÙĪ
    0.08
    bounds
    0.08
    æľªæĿ¥
    0.08
    Activations Density 0.472%

    No Known Activations