© 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. 3223
    Prev
    Next
    INDEX
    Explanations

    Seville, Bosnia, lymph

    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
     ski
    -0.36
    é«ĺåİŁ
    -0.32
     Alpine
    -0.32
     Rockies
    -0.31
    éĽªå±±
    -0.31
     Snow
    -0.31
     mountain
    -0.31
     skiing
    -0.30
    æ»ijéĽª
    -0.30
     Himal
    -0.29
    POSITIVE LOGITS
     маÑģло
    0.25
     Cairo
    0.24
    第ä¸ī人
    0.24
    æµĶ
    0.23
     Presidency
    0.23
    åŁł
    0.23
    theros
    0.23
    isms
    0.23
    ç¹ģå¿Ļ
    0.22
    å¬ĸ
    0.22
    Activations Density 0.101%

    No Known Activations