© 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. 60606
    Prev
    Next
    INDEX
    Explanations

    affiliate programs, links, advertising

    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
    æŃĮèĪŀ
    -0.09
     Tal
    -0.09
    æħĭ
    -0.08
    ani
    -0.08
    orns
    -0.08
    avage
    -0.08
    ç«ŀä»·
    -0.08
    çĪ±åIJĥ
    -0.08
    ened
    -0.08
     ÅĽm
    -0.08
    POSITIVE LOGITS
    çľ¨çľ¼
    0.09
    åĴĮæĬĢæľ¯
    0.08
    çļĩ
    0.08
    clare
    0.08
    ASP
    0.08
    å±ł
    0.08
    ValuePair
    0.08
    OSP
    0.08
    æĢ»éĥ¨
    0.08
    鼨
    0.08
    Activations Density 0.015%

    No Known Activations