© 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. 29575
    Prev
    Next
    INDEX
    Explanations

    phone number and contact

    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
    ohn
    -0.10
    à¹Į
    -0.09
    shaw
    -0.09
    stype
    -0.09
    onte
    -0.09
    ÙĪÙĨ
    -0.09
    èĢĨ
    -0.08
     tá»ij
    -0.08
    uer
    -0.08
    ãģĦãĤĭ
    -0.08
    POSITIVE LOGITS
     chóng
    0.10
    åįī
    0.10
    лег
    0.10
    hoot
    0.09
    blas
    0.09
    bles
    0.09
    ä¸ĢæĹı
    0.09
    isify
    0.09
    posite
    0.09
    casts
    0.09
    Activations Density 0.019%

    No Known Activations