© 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. 38760
    Prev
    Next
    INDEX
    Explanations

    Supreme Court

    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
    鼯
    -0.10
    elin
    -0.10
    æĸŃè£Ĥ
    -0.09
    å·²ä¹ħçļĦ
    -0.09
    éªł
    -0.09
    åIJĦæĸ¹éĿ¢
    -0.09
    æĹºçĽĽ
    -0.09
    à´Ļ
    -0.09
    ä¾Ĩèĩª
    -0.08
    媳å¦ĩ
    -0.08
    POSITIVE LOGITS
    人çī©
    0.09
    _PTR
    0.09
     гаÑĢ
    0.09
    .sparse
    0.09
    对å¾ħ
    0.08
    ÙģÙĦ
    0.08
    åĵ¡
    0.08
    airs
    0.08
    æѤæŶ
    0.08
    åħ³éĶ®æŶåĪ»
    0.08
    Activations Density 0.038%

    No Known Activations