© 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. 55904
    Prev
    Next
    INDEX
    Explanations

    course of

    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
    çĶļèĩ³è¿ŀ
    -0.10
    imens
    -0.10
    åģĩæĹ¥
    -0.10
    è¿Ļä¹Ī说
    -0.10
    аÑĨи
    -0.09
    èĽŃ
    -0.09
     возможноÑģÑĤÑĮ
    -0.09
    .Focused
    -0.09
    çĿ¡åīį
    -0.09
    æIJº
    -0.09
    POSITIVE LOGITS
     вÑģей
    0.09
    assel
    0.08
    æķ´åĢĭ
    0.08
    ä¸Ģ天
    0.08
    strain
    0.08
    æķ´ä¸ª
    0.08
    ä¸įéĶĻçļĦ
    0.08
     Soph
    0.07
    æĶ¾åĪ°
    0.07
    ä¹Łæĺ¯ä¸Ģ个
    0.07
    Activations Density 0.008%

    No Known Activations