© 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. 3179
    Prev
    Next
    INDEX
    Explanations

    subject, topic, matter

    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
     operations
    -0.23
    级åĪ«
    -0.21
    åī¥ç¦»
    -0.21
    å®ĮæĪIJäºĨ
    -0.21
     Machine
    -0.21
    åıªè¦ģæľī
    -0.21
    ç»ıèIJ¥æ´»åĬ¨
    -0.21
    çĶ¨æĿ¥
    -0.21
     functions
    -0.20
    æĵįä½ľ
    -0.20
    POSITIVE LOGITS
     matter
    0.35
    matter
    0.30
     matters
    0.29
     topic
    0.28
     regarding
    0.27
     mattered
    0.27
    topic
    0.26
    -topic
    0.26
     Matters
    0.26
    (topic
    0.26
    Activations Density 0.054%

    No Known Activations