© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3429
    Prev
    Next
    INDEX
    Explanations

    Asian Americans, Obama, California

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Circus
    -0.29
    泺
    -0.25
    äºĨåįĬ天
    -0.23
     desperation
    -0.23
    çĭĤ欢
    -0.22
     performer
    -0.22
    incess
    -0.21
     decad
    -0.21
     Horror
    -0.21
    ulp
    -0.21
    POSITIVE LOGITS
    èĵĦ
    0.30
    è£Ķ
    0.29
     Wyoming
    0.29
     Daniels
    0.28
     california
    0.28
     USDA
    0.28
     California
    0.28
     Oregon
    0.27
    PEND
    0.27
     Utah
    0.26
    Activations Density 0.017%

    No Known Activations