© 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. 8192
    Prev
    Next
    INDEX
    Explanations

    environment, motor, wheels, play

    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
    æĭħè´Ł
    -0.10
    æĬ½åıĸ
    -0.09
    æĢ§åij½
    -0.09
    å¾Īæĸ¹ä¾¿
    -0.09
    æĤ´
    -0.08
     PropertyInfo
    -0.08
    imens
    -0.08
    åIJĥä»Ģä¹Ī
    -0.08
    rgan
    -0.08
    æīģ
    -0.08
    POSITIVE LOGITS
    çݯå¢ĥä¸Ń
    0.11
    丰å¯Į
    0.10
    åħħå®ŀ
    0.10
    çݯå¢ĥ
    0.10
     environment
    0.09
    åĨ²
    0.09
    åģ¥
    0.09
    åħħ
    0.09
    environment
    0.09
    thrown
    0.09
    Activations Density 0.066%

    No Known Activations