© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1048
    Prev
    Next
    INDEX
    Explanations

    folic acid, pregnancy, prenatal, embryo

    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
    Not in Any Lists

    No Comments

    Negative Logits
     coward
    -0.27
     glob
    -0.25
    anni
    -0.24
    è¾ĺ
    -0.24
    -cluster
    -0.24
    æĪĺæľ¯
    -0.24
    omm
    -0.23
    glob
    -0.23
    æľ½
    -0.23
     barrels
    -0.23
    POSITIVE LOGITS
    éĶĮ
    0.32
    éĶ°
    0.29
     Vitamin
    0.29
    ç»´çĶŁç´ł
    0.28
     vitamin
    0.28
     zinc
    0.28
    åĩĨ
    0.28
     manganese
    0.27
    ãĤµãĥĹãĥª
    0.26
     vitamins
    0.26
    Activations Density 0.012%

    No Known Activations