© 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. 29522
    Prev
    Next
    INDEX
    Explanations

    prizes and gifts

    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
    å¦ĤæѤ
    -0.09
    èµŃ
    -0.09
    æĪijåĴĮ
    -0.08
    åĹ¡
    -0.08
    yme
    -0.08
    æīĢéľĢè¦ģ
    -0.08
     mãi
    -0.08
    oday
    -0.08
    olley
    -0.08
    çIJ¯
    -0.08
    POSITIVE LOGITS
    æ¯ıä½į
    0.12
    æ¯ıä¸Ģä½į
    0.10
    伤亡
    0.09
    äºĮ次
    0.09
    è¿ĩåħ³
    0.09
    å¼ĢæľĹ
    0.08
    èĭ¥å¹²
    0.08
    ä¸Ĭå²Ĺ
    0.08
    éŸ
    0.08
    èĥľè´Ł
    0.08
    Activations Density 0.007%

    No Known Activations