© 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. 746
    Prev
    Next
    INDEX
    Explanations

    quim/quillian/quimal

    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
    ium
    -0.12
    ë£Į
    -0.10
    uka
    -0.09
    ç³Ĭæ¶Ĥ
    -0.09
    ä¸Ģ棵
    -0.09
    à¸Ļำ
    -0.09
    liness
    -0.09
    åĨįåĬłä¸Ĭ
    -0.09
    fully
    -0.09
    utto
    -0.09
    POSITIVE LOGITS
    ãģ¹ãģį
    0.11
    éĽ³
    0.10
    éľīç´ł
    0.10
    çĦ¶æĺ¯
    0.10
    adir
    0.09
    ipment
    0.09
    ãģ¦ãĤĤ
    0.09
    æĸ¯åĿ¦
    0.09
    naire
    0.09
    /or
    0.09
    Activations Density 0.116%

    No Known Activations