© 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. 40096
    Prev
    Next
    INDEX
    Explanations

    Bradford Northern

    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
    éĤ£ä¹Ī容æĺĵ
    -0.11
    å°ĸ
    -0.10
    媳
    -0.09
    tics
    -0.09
    以èī²
    -0.09
    çIJ¶
    -0.09
    çıĢ
    -0.09
    äºŁ
    -0.09
    å¾Ĺä¸įåĪ°
    -0.09
    iginal
    -0.09
    POSITIVE LOGITS
     Eag
    0.09
    ä»·
    0.09
    iaux
    0.09
    é¢Ĩ导ä¸ĭ
    0.08
    anders
    0.08
    üst
    0.08
    人士
    0.08
    ltra
    0.08
    æŀ¨
    0.08
     Spir
    0.08
    Activations Density 0.005%

    No Known Activations