© 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. 14285
    Prev
    Next
    INDEX
    Explanations

    specific locations

    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
    ç©·
    -0.21
    entropy
    -0.20
    chine
    -0.19
     chromat
    -0.19
    SHARE
    -0.19
    åŀ¡
    -0.19
    åī¥å¤º
    -0.19
    éĴĮ
    -0.19
    _was
    -0.18
    ias
    -0.18
    POSITIVE LOGITS
    çĭ¬çī¹çļĦ
    0.27
    çļĦä¼ĺåĬ¿
    0.26
    ä¼ĺåĬ¿
    0.26
    ä¼ĺè¶Ĭ
    0.25
    éĢĤåIJĪ
    0.25
    çļĦçĭ¬çī¹
    0.25
    æľīè¿Ļæł·çļĦ
    0.25
    çĭ¬çī¹
    0.24
    以åħ¶
    0.23
    åı¯ä¾Ľ
    0.23
    Activations Density 0.130%

    No Known Activations