© 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. 60715
    Prev
    Next
    INDEX
    Explanations

    religious groups and places

    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
    orris
    -0.10
    amac
    -0.10
    ì¾Į
    -0.09
    éĺŁ
    -0.09
    -Sah
    -0.09
    iminary
    -0.09
     cleared
    -0.09
    íĺ¼
    -0.09
     charged
    -0.08
    JE
    -0.08
    POSITIVE LOGITS
    ois
    0.10
    thal
    0.08
    åĴĦ
    0.08
    è¦Ĩ
    0.08
    bare
    0.08
    åħ¨éĿ¢åıijå±ķ
    0.08
    å®Į好
    0.08
    ãģĽãģĦ
    0.08
    ç½ijé¦ĸ页
    0.08
    رات
    0.08
    Activations Density 0.013%

    No Known Activations