© 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. 3140
    Prev
    Next
    INDEX
    Explanations

    rock bands

    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
    鸣类
    -0.26
    鸣
    -0.24
     Pride
    -0.24
    ä½ļ
    -0.24
    Anonymous
    -0.24
    éĽªèĬ±
    -0.23
    éĤ£äºº
    -0.23
    ä¸įåı¯æĢĿè®®
    -0.23
     tweeting
    -0.23
    æĸĩç§ij
    -0.23
    POSITIVE LOGITS
    æ²¹
    0.33
     oil
    0.32
    oil
    0.31
    Oil
    0.29
     Oil
    0.29
    çŁ³æ²¹
    0.28
     oils
    0.28
    æ²¹æ°Ķ
    0.27
    æ²¹çĶ°
    0.27
    缦
    0.25
    Activations Density 0.010%

    No Known Activations