© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15291
    Prev
    Next
    INDEX
    Explanations

    wireless accounts, Disney films, oil tycoons, Russia districts, express static, nuclear reactors, wellbores

    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
     vern
    -0.18
    tml
    -0.17
     bleed
    -0.17
    isen
    -0.17
     trump
    -0.17
    å²ŃåįĹ
    -0.17
    åįĥ
    -0.17
    åĴĮå®ĮåĸĦ
    -0.17
    æĬĢæľ¯åĴĮ
    -0.17
    建设åĴĮ
    -0.16
    POSITIVE LOGITS
     Classic
    0.20
    å°±ä¸ļå²Ĺä½į
    0.19
    æĥ¨
    0.18
     Morrow
    0.17
    ski
    0.17
    äºĮ线
    0.17
    大éĻĨ
    0.16
    俸
    0.16
    ãĤ·ãĤ¢
    0.16
    éĤ¶
    0.16
    Activations Density 0.351%

    No Known Activations