© 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. 2756
    Prev
    Next
    INDEX
    Explanations

    next generation

    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
    æ¼ķ
    -0.10
    æ©IJ
    -0.09
    à¹ĥà¸Ī
    -0.09
    èµŀæĪIJ
    -0.09
    ç¼ļ
    -0.09
    /oauth
    -0.09
    è¡·
    -0.08
    enstein
    -0.08
    è¿Ļ个è¡Įä¸ļ
    -0.08
    umo
    -0.08
    POSITIVE LOGITS
    æŀ¢
    0.10
    iali
    0.09
    -old
    0.09
    æľªå©ļ
    0.09
    继ç»Ńä¿ĿæĮģ
    0.08
    urons
    0.08
     Wor
    0.08
    ality
    0.08
    ç»Ļ她
    0.08
     bra
    0.08
    Activations Density 0.029%

    No Known Activations