© 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. 3177
    Prev
    Next
    INDEX
    Explanations

    software and specific topics

    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
    otto
    -0.23
    裹
    -0.22
    vey
    -0.21
    à¹Ģย
    -0.21
     Cond
    -0.21
    sut
    -0.20
     haze
    -0.20
    åĬ¨äºº
    -0.20
     seaside
    -0.20
    /loading
    -0.20
    POSITIVE LOGITS
    æĪĸèĢħåħ¶ä»ĸ
    0.23
    ä¸Ńå¿ĥåŁİåĮº
    0.23
    人次
    0.23
     counterpart
    0.22
    ä¸įåħį
    0.21
    çļĦè§ĤçĤ¹
    0.21
    åĽ½ç«ĭ
    0.21
    æľ¬èº«çļĦ
    0.20
    人为
    0.20
    彩
    0.20
    Activations Density 0.288%

    No Known Activations