© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2629
    Prev
    Next
    INDEX
    Explanations

    company names and brands

    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
     institutes
    -0.27
    éĩijèŀįæľºæŀĦ
    -0.27
    ä¸ļçķĮ
    -0.26
    ><!--
    -0.25
    dera
    -0.24
    otron
    -0.24
    æĪIJåĬŁçİĩ
    -0.24
    ä¸ĢæīĢ
    -0.23
    afia
    -0.23
    POOL
    -0.23
    POSITIVE LOGITS
     brand
    0.45
    ®
    0.40
    ç³»åĪĹ产åĵģ
    0.38
    çīĮ
    0.35
    åĵģçīĮ
    0.34
     brands
    0.34
     products
    0.32
    åĵģçīĮçļĦ
    0.31
     product
    0.31
     ®
    0.29
    Activations Density 0.027%

    No Known Activations