© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56333
    Prev
    Next
    INDEX
    Explanations

    down payment, exchange, note, options

    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
     Curtain
    -0.09
    欹
    -0.09
    工夫
    -0.09
     dynasty
    -0.08
    æĻ´
    -0.08
    æµ´
    -0.08
     Woj
    -0.08
    æIJĢ
    -0.08
    港
    -0.08
    ÑģеÑĤ
    -0.08
    POSITIVE LOGITS
    antan
    0.11
    ä¼ı
    0.09
    æīĢæľīæĿĥ
    0.09
    ä¸Ģé¢Ĺ
    0.09
    åįıè®®
    0.09
    anan
    0.09
    ä»ĺ款
    0.09
    é¦ĸä»ĺ
    0.09
    APE
    0.09
    å¾ĹäºĨ
    0.09
    Activations Density 0.066%

    No Known Activations