© 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. 6157
    Prev
    Next
    INDEX
    Explanations

    Bruce followed by surname

    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
    ../../../
    -0.12
    roit
    -0.11
    th
    -0.11
    rese
    -0.11
    ãģıãĤĮ
    -0.10
    ÑĦеÑĢ
    -0.10
    reur
    -0.10
    reas
    -0.10
    reme
    -0.10
    re
    -0.10
    POSITIVE LOGITS
    holder
    0.10
    0
    0.10
    lessly
    0.09
    åī¯ä¹¦è®°
    0.09
    y
    0.09
    è¯ŀ
    0.09
    andal
    0.09
    9
    0.09
    ele
    0.09
    yla
    0.09
    Activations Density 0.010%

    No Known Activations