© 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. 8047
    Prev
    Next
    INDEX
    Explanations

    tennis tournaments or ATP Tour

    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
    åıĤå±ķ
    -0.10
    åħ¨çľģ
    -0.09
    çĸ¤
    -0.09
    å±ķ
    -0.09
     temp
    -0.09
    çĶ¨æīĭ
    -0.09
    å±ķä½į
    -0.09
    çľģåĨħ
    -0.09
    ddit
    -0.08
    å±ķåĮº
    -0.08
    POSITIVE LOGITS
    åĽĽå¤Ħ
    0.10
    .arc
    0.10
    å¹´æľ«
    0.09
     sÃłn
    0.09
    å¹´åºķ
    0.09
    æµģæ°´
    0.08
    ç¹ģ
    0.08
    åIJ¸æ¯Ĵ
    0.08
    åIJĦ大
    0.08
     lifestyle
    0.08
    Activations Density 0.173%

    No Known Activations