© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6106
    Prev
    Next
    INDEX
    Explanations

    Christ received

    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
    Negative Logits
    ãģ£ãģ±
    -0.11
    igma
    -0.08
    éŃħåĬĽ
    -0.08
    åħ¬ç«ĭåĮ»éĻ¢
    -0.08
    ä¹ĭæīĢ
    -0.08
    inder
    -0.08
    éĿĴ
    -0.08
    æľIJ
    -0.08
     Zodiac
    -0.08
    åĵĪåĵĪ
    -0.08
    POSITIVE LOGITS
    ä¸įä¸ĭ
    0.11
    æ¦Ķ
    0.10
    éļĶ
    0.09
     mig
    0.09
    ALAR
    0.08
    æĭ¢
    0.08
     Paras
    0.08
    Unavailable
    0.08
    èĦ
    0.08
    è·³åĩº
    0.08
    Activations Density 0.009%

    No Known Activations