© 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. 60818
    Prev
    Next
    INDEX
    Explanations

    rise in or rise of

    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
    ´
    -0.10
    ting
    -0.10
    ãģĦãģĨ
    -0.10
     forthcoming
    -0.10
    stration
    -0.09
    rina
    -0.09
    à¦ĸ
    -0.09
    tes
    -0.09
    å®ŀæĥł
    -0.09
    ÑĢин
    -0.09
    POSITIVE LOGITS
    åĴĮå®ĮåĸĦ
    0.12
    quel
    0.12
    mary
    0.10
    /stretch
    0.10
    0.10
    iard
    0.10
    olate
    0.10
    idon
    0.10
     дов
    0.09
    aunch
    0.09
    Activations Density 0.029%

    No Known Activations