© 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. 15007
    Prev
    Next
    INDEX
    Explanations

    investigating a complaint Tuesday

    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
    åĩºäºĨ
    -0.18
     rather
    -0.18
    QUIRE
    -0.18
     fine
    -0.18
    æŨ
    -0.17
    ANNEL
    -0.17
    èĢĮéĿŀ
    -0.17
    dale
    -0.17
    èĢĮä¸įæĺ¯
    -0.17
     coupons
    -0.17
    POSITIVE LOGITS
    æĬ¥æ¡Ī
    0.26
    æ¶Ĥ
    0.24
    履约
    0.23
    æĬ¥åijĬæĺ¾ç¤º
    0.23
    åĩºåĬ¨
    0.22
    æĪ¾
    0.22
    éĢļæĬ¥
    0.21
    çİ°åľº
    0.21
    è§Ħ模æľĢ大
    0.21
    åľ¨çİ°åľº
    0.21
    Activations Density 0.023%

    No Known Activations