© 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. 26240
    Prev
    Next
    INDEX
    Explanations

    learning on one's own

    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
    第ä¸ĢæĿ¡
    -0.10
    人æīįåŁ¹åħ»
    -0.09
     Libert
    -0.09
    roach
    -0.09
    esc
    -0.09
    è¡Įä¸ļåĨħ
    -0.09
    æķ´ä¸ªäºº
    -0.09
    дей
    -0.08
    人æīį
    -0.08
    沩
    -0.08
    POSITIVE LOGITS
    èĩªåѦ
    0.16
    èĩªä¹ł
    0.12
    èĩªä¸»
    0.11
    诵
    0.10
    çľĭ书
    0.10
    åłĥ
    0.09
    课å¤ĸ
    0.09
     ÑģамоÑģÑĤоÑıÑĤелÑĮно
    0.09
     self
    0.09
    èĩªè§ī
    0.09
    Activations Density 0.073%

    No Known Activations