© 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. 3266
    Prev
    Next
    INDEX
    Explanations

    Price and numerical expressions

    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
    bestos
    -0.24
    pecially
    -0.24
    esome
    -0.23
    едеÑĢ
    -0.23
    iliar
    -0.23
    iele
    -0.23
    IPLE
    -0.23
    OURSE
    -0.23
    bsites
    -0.23
    OULD
    -0.22
    POSITIVE LOGITS
    两åı¥
    0.24
    ä»·æł¼ä¸Ĭ涨
    0.23
    æĻĵå¾Ĺ
    0.22
     Notes
    0.22
    æĪijçĪ±ä½ł
    0.21
    éļ¾åıĹ
    0.21
    ä»Ģä¹ĪæĦıæĢĿ
    0.21
    æĿ¿æĿIJ
    0.21
    ä¸ĢéĹª
    0.21
     Conditions
    0.20
    Activations Density 0.226%

    No Known Activations