© 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. 13332
    Prev
    Next
    INDEX
    Explanations

    sharing responsibility provisions

    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
    æĪij们就
    -0.19
    èĥ³
    -0.18
     surg
    -0.18
    å¾Īå¤ļäºĭæĥħ
    -0.18
    imits
    -0.18
    ãģ«ãģª
    -0.18
    ç±į
    -0.18
    主线
    -0.18
    å½±åĵįåĬĽ
    -0.17
    解åĨ³éĹ®é¢ĺ
    -0.17
    POSITIVE LOGITS
    venues
    0.19
    æĥ®
    0.19
    ä¿ļ
    0.19
    é¾ĥ
    0.19
    åĮ®
    0.19
    éªĭ
    0.18
    æ½ŀ
    0.18
     Staples
    0.18
    èĵ¼
    0.18
    æļ
    0.17
    Activations Density 0.002%

    No Known Activations