© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6887
    Prev
    Next
    INDEX
    Explanations

    fair trade, social, environmental

    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
    eted
    -0.10
    èħ¼
    -0.09
    otor
    -0.09
     bureaucr
    -0.09
    åĭĥ
    -0.09
    åºĹéĿ¢
    -0.09
    æľªæĪIJ
    -0.09
    å±ħå§Ķä¼ļ
    -0.09
    éĽ¾éľ¾
    -0.09
    ëŀ¨
    -0.09
    POSITIVE LOGITS
    åħ¬å¹³
    0.10
    éĨĴ
    0.10
    èĢĥè¯Ħ
    0.09
    anga
    0.09
     Signature
    0.09
    æľ¬åľ°
    0.08
    aldi
    0.08
     Mond
    0.08
    交å¾Ģ
    0.08
    ongo
    0.08
    Activations Density 0.058%

    No Known Activations