© 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. 59163
    Prev
    Next
    INDEX
    Explanations

    religious and ethnic groups

    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
    Not in Any Lists

    No Comments

    Negative Logits
    å°ijä¸įäºĨ
    -0.10
    ç¬Ķ
    -0.09
    lette
    -0.09
    æݥ触åĪ°
    -0.09
    æĪ¡
    -0.08
    èĥ½è®©
    -0.08
    åįĬå²Ľ
    -0.08
    éĢĶå¾Ħ
    -0.08
    åīĮ
    -0.08
    typeof
    -0.08
    POSITIVE LOGITS
     GAR
    0.09
    strument
    0.09
    enk
    0.08
     Athletic
    0.08
    ä¸ĬçıŃ
    0.08
     SIG
    0.08
    为主è¦ģ
    0.08
    为主çļĦ
    0.08
    é¦ĸ
    0.08
    CPP
    0.08
    Activations Density 0.056%

    No Known Activations