© 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. 12283
    Prev
    Next
    INDEX
    Explanations

    art and related concepts

    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
    naire
    -0.10
    /generated
    -0.09
    .sg
    -0.09
    -addons
    -0.09
    \Contracts
    -0.09
    oret
    -0.09
    æļ®
    -0.09
     MIT
    -0.09
    mage
    -0.09
    zelf
    -0.09
    POSITIVE LOGITS
    ifice
    0.11
    çķĮçļĦ
    0.11
    ä¸įç»ı
    0.10
    istry
    0.09
    称ä¹ĭ
    0.09
    åı²ä¸Ĭ
    0.08
    uality
    0.08
    form
    0.08
    fulness
    0.08
    å½¢å¼ı
    0.08
    Activations Density 0.017%

    No Known Activations