© 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. 3365
    Prev
    Next
    INDEX
    Explanations

    natural resources, minerals, oil, and reserves

    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
     forwarding
    -0.31
    书éĿ¢
    -0.29
     personal
    -0.26
    æijĨæĶ¾
    -0.25
    ä½ľé£İ
    -0.24
     Toast
    -0.24
     vign
    -0.23
     дейÑģÑĤвие
    -0.23
     DONE
    -0.23
    åĬ¨ä½ľ
    -0.23
    POSITIVE LOGITS
    åĤ¨éĩı
    0.59
    å¼Ģéĩĩ
    0.47
    æ½ľåĬĽ
    0.45
     explo
    0.39
    èµĦæºIJ
    0.38
     undis
    0.37
    è³ĩæºIJ
    0.36
    å¼ĢåıijåĪ©çĶ¨
    0.36
     mined
    0.36
    åĭĺæİ¢
    0.36
    Activations Density 0.030%

    No Known Activations