© 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. 6148
    Prev
    Next
    INDEX
    Explanations

    anyone who

    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
     Ñģами
    -0.10
    æ¯ıä½į
    -0.10
    æīĢæľīçļĦ
    -0.09
    åIJĦé¡¹å·¥ä½ľ
    -0.09
     вÑģего
    -0.09
    æľīçļĦ
    -0.09
    æ¯ıä¸Ģä½į
    -0.09
     دائÙħا
    -0.09
    æĺĬ
    -0.09
    å°ī
    -0.09
    POSITIVE LOGITS
    elin
    0.10
     Fet
    0.09
     else
    0.09
    åħ¶éĹ´
    0.09
     Pett
    0.09
    èİŀ
    0.09
    otron
    0.09
    ä½ĵä¼ļåĪ°
    0.09
    icit
    0.08
    ARB
    0.08
    Activations Density 0.030%

    No Known Activations