© 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. 36076
    Prev
    Next
    INDEX
    Explanations

    Joe followed by surname

    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
    ness
    -0.11
    çĦ¶æĺ¯
    -0.10
    ãģĹãģ¾ãģĨ
    -0.10
    å¯ŀ
    -0.09
    ãģĦãģ¾ãģĻãģĮ
    -0.09
    orious
    -0.09
    æĢ§å¼º
    -0.09
    лиÑĩ
    -0.09
    à¹Į
    -0.09
    ãģĦãģ¾ãģĻ
    -0.09
    POSITIVE LOGITS
    ptions
    0.10
    lement
    0.10
    -fashioned
    0.09
    gether
    0.09
    ffer
    0.09
    лÑİ
    0.09
    crow
    0.09
    isplay
    0.09
    éric
    0.09
    ster
    0.08
    Activations Density 0.051%

    No Known Activations