© 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. 3194
    Prev
    Next
    INDEX
    Explanations

    natural foods and compounds

    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
     arrang
    -0.27
    ä¸į稳å®ļ
    -0.27
     nghiá»ĩp
    -0.25
    è¿Ĥ
    -0.25
    ä¸īæĸ¹
    -0.23
    èĻļ空
    -0.23
     edi
    -0.23
    æ±IJ
    -0.23
    ä¸Ĭä¸ĭ
    -0.23
    lop
    -0.23
    POSITIVE LOGITS
    å¯ĮåIJ«
    0.41
    åIJ«æľī
    0.38
    ä¸ŃåIJ«æľī
    0.37
     beneficial
    0.32
     antioxidants
    0.31
    æĬĹæ°§åĮĸ
    0.31
     Contains
    0.30
     calorie
    0.30
     contains
    0.29
    ioxid
    0.29
    Activations Density 0.075%

    No Known Activations