© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2091
    Prev
    Next
    INDEX
    Explanations

    and followed by descriptors

    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
    ãĤ¢ãĤ¦
    -0.11
    æĢ§å¼º
    -0.11
    ä¹ĥèĩ³
    -0.11
    ity
    -0.10
    wow
    -0.10
    带头人
    -0.09
    æĢ§çļĦ
    -0.09
    çĶļèĩ³æĺ¯
    -0.09
    ãģ¶
    -0.09
    æľĢ强
    -0.09
    POSITIVE LOGITS
    åĶ¿
    0.10
    ex
    0.09
    åĴ¸
    0.08
     оÑĦоÑĢмлен
    0.08
    èģĮ
    0.08
    æĪijåıĪ
    0.08
    ening
    0.08
    桧
    0.08
    coop
    0.08
    åĪ©äºİ
    0.08
    Activations Density 0.126%

    No Known Activations