© 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. 23954
    Prev
    Next
    INDEX
    Explanations

    Adobe software and analytics

    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
    å¿ĹæĦ¿
    -0.10
     ASP
    -0.09
     pl
    -0.08
     condensed
    -0.08
    ained
    -0.07
    rain
    -0.07
    cached
    -0.07
    argo
    -0.07
    åıĭ
    -0.07
     Cass
    -0.07
    POSITIVE LOGITS
    Adobe
    0.11
     Adobe
    0.10
    代çIJĨåķĨ
    0.09
     Acrobat
    0.09
    ç½ļ
    0.09
    éĩİ
    0.09
    æķ¦çħĮ
    0.09
     webinar
    0.09
    byn
    0.09
    HING
    0.09
    Activations Density 0.063%

    No Known Activations