© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14590
    Prev
    Next
    INDEX
    Explanations

    suffixes like ia, or, anto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     Äijen
    -0.23
     nắng
    -0.23
    åĬłåĽº
    -0.22
    åŁ¤
    -0.20
    éĩľ
    -0.20
    骡
    -0.19
    gue
    -0.18
    å¨ĩ
    -0.18
     Yorkers
    -0.18
    åĴĮæĬĢæľ¯
    -0.18
    POSITIVE LOGITS
     Tolkien
    0.32
    ä¹IJåĽŃ
    0.20
     languages
    0.20
    prot
    0.20
    olkien
    0.19
    ä¸ĸçķĮè§Ĥ
    0.19
     Erl
    0.19
    è¯ŀ
    0.19
     backyard
    0.18
     Hos
    0.18
    Activations Density 0.009%

    No Known Activations