© 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. 3402
    Prev
    Next
    INDEX
    Explanations

    courtship and mating behavior

    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
    acci
    -0.27
     movers
    -0.25
     baked
    -0.25
    èµ·æŃ¥
    -0.25
    affe
    -0.24
    人æ°ijå¸ģ
    -0.23
    ä¸Ńåįİ人æ°ij
    -0.23
    -parts
    -0.23
     CIT
    -0.23
     stap
    -0.23
    POSITIVE LOGITS
    éĽĮ
    0.52
     females
    0.43
     males
    0.43
     mascul
    0.43
     mating
    0.42
     sexually
    0.41
    Female
    0.40
     male
    0.39
     female
    0.39
    æĢ§åĪ«
    0.39
    Activations Density 0.078%

    No Known Activations