© 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. 36470
    Prev
    Next
    INDEX
    Explanations

    control centre or region

    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
    带åĬ¨
    -0.11
     supra
    -0.09
    åĬŀåѦ
    -0.09
    æħķ
    -0.09
    æºIJæºIJ
    -0.09
    .Ribbon
    -0.09
    -alist
    -0.09
    åŃ³
    -0.08
    rides
    -0.08
    æIJº
    -0.08
    POSITIVE LOGITS
    è°ĥ度
    0.11
    æĹłçº¿çĶµ
    0.10
    ä¸Ĭå²Ĺ
    0.10
    çĭ¼
    0.10
    èģĮè´£
    0.10
    å²Ĺä½į
    0.10
    ãĥªãĤ¢ãĥ«
    0.10
    ä¸Ńæŀ¢
    0.09
    åĺ¹
    0.09
    åĢ¼å®Ī
    0.09
    Activations Density 0.094%

    No Known Activations