© 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. 3141
    Prev
    Next
    INDEX
    Explanations

    immigrant and migrant contexts

    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
    ignment
    -0.23
    é²²
    -0.22
    ä¸Ģ款
    -0.22
    大纲
    -0.22
    ëį°
    -0.21
    åĩºåĵģ
    -0.21
    æĹ©çĤ¹
    -0.21
     Indoor
    -0.20
    严å¯Ĩ
    -0.20
    åī¯ä¸»ä»»
    -0.20
    POSITIVE LOGITS
    éĿ¢åŃĶ
    0.25
     families
    0.25
    /ref
    0.22
     dwelling
    0.22
    dw
    0.21
     dwell
    0.21
     arrivals
    0.21
    åħ·æľīèī¯å¥½
    0.20
    -friendly
    0.20
     populations
    0.20
    Activations Density 0.006%

    No Known Activations