© 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. 3421
    Prev
    Next
    INDEX
    Explanations

    specialty, precision, luxury, fine

    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
    æĪŁ
    -0.24
     Routine
    -0.24
    utzer
    -0.21
     Thoughts
    -0.21
    ä¾ĭè¡Į
    -0.21
    amb
    -0.21
     prompt
    -0.20
     examiner
    -0.20
    çĨ
    -0.20
     kot
    -0.20
    POSITIVE LOGITS
    ä¹ĭä½ľ
    0.32
     Juda
    0.30
    æľīæľº
    0.26
    åIJĦå¼Ĥ
    0.25
    ç»Ĩ
    0.24
    人士
    0.24
    æ°´åĩĨ
    0.24
    -style
    0.24
    ishly
    0.23
    æ··åIJĪ
    0.23
    Activations Density 0.024%

    No Known Activations