© 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. 3224
    Prev
    Next
    INDEX
    Explanations

    athletics championships

    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
     haircut
    -0.23
    çļij
    -0.21
    大éģĵ
    -0.21
    æ´ĭèij±
    -0.21
    è±ķ
    -0.21
    çıŃ主任
    -0.21
    åŃ¦æľŁ
    -0.21
    _TCP
    -0.21
    Enumerator
    -0.21
    .Dot
    -0.21
    POSITIVE LOGITS
    æĴŃ
    0.23
    åĽ½å®¶éĺŁ
    0.23
    lando
    0.22
    lations
    0.22
    å·´é»İ
    0.22
    è·ĭ
    0.22
    /by
    0.22
    layan
    0.21
    åĩºäºİ
    0.21
     legacy
    0.21
    Activations Density 0.005%

    No Known Activations