© 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. 16716
    Prev
    Next
    INDEX
    Explanations

    —or, —and, —the

    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
    ãĥ¥
    -0.10
    ãĥ³
    -0.10
    ity
    -0.10
    he
    -0.09
    anja
    -0.09
     jun
    -0.08
    doc
    -0.08
    ãģĦ
    -0.08
    ython
    -0.08
    ildo
    -0.08
    POSITIVE LOGITS
    ings
    0.13
    INGS
    0.11
    ered
    0.09
     Sacred
    0.09
    onym
    0.09
    ä¸ŃåİŁ
    0.09
    翦
    0.08
    NESS
    0.08
    isms
    0.08
    ivityManager
    0.08
    Activations Density 0.048%

    No Known Activations