© 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. 7752
    Prev
    Next
    INDEX
    Explanations

    wwe chairman Vince McMahon

    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
    åħ¶ä»ĸçļĦ
    -0.10
    ç¾İ丽çļĦ
    -0.09
    ä¸ĢåĿĹ
    -0.08
     Burgess
    -0.08
     Cyr
    -0.08
    å¸ĥ
    -0.08
     Bowman
    -0.08
    iek
    -0.08
     Emb
    -0.08
     обÑıзан
    -0.08
    POSITIVE LOGITS
    OMETRY
    0.10
    ä¸įäºĨ
    0.09
    ingroup
    0.09
    еÑĢÑĤ
    0.09
    ingleton
    0.09
    rades
    0.09
    楮
    0.09
    ooter
    0.09
     TestUtils
    0.09
    æĪİ
    0.09
    Activations Density 0.095%

    No Known Activations