© 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. 3240
    Prev
    Next
    INDEX
    Explanations

    green tea

    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
     Invisible
    -0.32
    åħ¬åħ±æĸĩåĮĸ
    -0.27
    titles
    -0.27
    å¢Ļä¸Ĭ
    -0.26
    åĮħ容
    -0.24
     endwhile
    -0.24
     invisible
    -0.24
    å¥Ķé©°
    -0.23
    容åĻ¨
    -0.23
    åIJĮåŁİ
    -0.23
    POSITIVE LOGITS
    èĮ¶åı¶
    0.42
     tea
    0.42
    绿èĮ¶
    0.39
    èĮ¶
    0.36
    èĮ¶åĽŃ
    0.35
    shan
    0.30
     Tea
    0.29
    åĸĿèĮ¶
    0.29
     Himal
    0.28
    ç¦ħ
    0.28
    Activations Density 0.010%

    No Known Activations