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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 265
    Prev
    Next
    INDEX
    Explanations

    food additives and ingredients

    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
    å¾Ĺ罪
    -0.28
     ÙħØŃÙħ
    -0.25
    æĬ¥ä»ĩ
    -0.25
    ç¬Ķè®°æľ¬
    -0.25
    åł¡åŀĴ
    -0.24
    å¤įä»ĩ
    -0.24
     ssh
    -0.24
     Exodus
    -0.23
    èĥ¸åīį
    -0.23
     warrior
    -0.23
    POSITIVE LOGITS
    æ·»åĬłåīĤ
    0.43
     additives
    0.40
    æ·»åĬł
    0.39
     added
    0.36
    é£Łåĵģ
    0.35
    æĪIJåĪĨ
    0.35
    -added
    0.33
    让æ¶Īè´¹èĢħ
    0.33
     ingredient
    0.32
     æ·»åĬł
    0.31
    Activations Density 0.061%

    No Known Activations