© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20253
    Prev
    Next
    INDEX
    Explanations

    among which are

    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
    orno
    -0.11
    åIJĦéĥ¨éŨ
    -0.10
    .sourceforge
    -0.09
    аÑĢам
    -0.09
    ä¸įåIJĮç±»åŀĭ
    -0.09
    infra
    -0.09
    æºī
    -0.09
    ainer
    -0.09
     otherwise
    -0.09
    (){}↵↵
    -0.09
    POSITIVE LOGITS
    ä¸įä¹ı
    0.11
    æģķ
    0.10
    æİ¢
    0.08
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.08
    odes
    0.08
    æĪijæĥ³
    0.08
    åħļå§Ķ书记
    0.08
    é¦ĸåħĪæĺ¯
    0.08
    als
    0.08
    çĤ¬
    0.08
    Activations Density 0.065%

    No Known Activations