© 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. 64122
    Prev
    Next
    INDEX
    Explanations

    Field of the Invention

    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
    achines
    -0.08
    ensions
    -0.08
    æľ¬åħ¬åı¸
    -0.07
    èĥĮçĿĢ
    -0.07
    agnar
    -0.07
    é«ĺå³°
    -0.07
    æĭīæĸ¯
    -0.07
    achinery
    -0.07
    ephy
    -0.07
    们
    -0.07
    POSITIVE LOGITS
     Thứ
    0.10
    èĪį
    0.09
     neglig
    0.08
    ÑĪка
    0.08
    baum
    0.08
    ãģ§ãģĤ
    0.08
    以èī²
    0.08
    ãĥīãĥ¬ãĤ¹
    0.08
     поÑĤом
    0.08
     Cain
    0.08
    Activations Density 3.739%

    No Known Activations