© 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. 29643
    Prev
    Next
    INDEX
    Explanations

    mortgage

    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
    обÑĢ
    -0.10
    ÑĤÑĢа
    -0.10
    ÙĤÙĪد
    -0.09
    åĦ¿å¥³
    -0.09
    зо
    -0.09
    éĦ¢
    -0.09
    ëģĶ
    -0.09
    аÑĤелÑĮ
    -0.09
    ARIO
    -0.08
    POSITIVE LOGITS
    ducible
    0.10
    mort
    0.10
    gether
    0.10
    baugh
    0.09
    ythe
    0.09
    isten
    0.09
    ship
    0.09
    chestra
    0.08
     Brilliant
    0.08
    lox
    0.08
    Activations Density 0.021%

    No Known Activations