© 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. 16660
    Prev
    Next
    INDEX
    Explanations

    doing business as (d/b/a)

    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
    çĽĹ
    -0.10
    对æĪij们
    -0.09
    swer
    -0.09
    æķ£æŃ¥
    -0.09
    lest
    -0.09
    åĸŁ
    -0.09
    è´¼
    -0.09
    ä¸Ģå¤ľ
    -0.08
    åºŁçī©
    -0.08
    ASK
    -0.08
    POSITIVE LOGITS
     Micha
    0.09
    èĥĮåIJİ
    0.09
    æĪ·
    0.08
    ëģ¼
    0.08
    phen
    0.08
    yaw
    0.08
    ä¼ł
    0.08
    çĸı
    0.08
     Welcome
    0.07
    _direct
    0.07
    Activations Density 0.007%

    No Known Activations