© 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. 16226
    Prev
    Next
    INDEX
    Explanations

    institution

    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
    ä¸ļçķĮ
    -0.22
    fty
    -0.20
    åı£åij³
    -0.20
    ridge
    -0.20
    yar
    -0.19
    å§Ķå®£ä¼łéĥ¨
    -0.19
    æľīæĦı
    -0.19
    çĪ½
    -0.19
    ä¸ļåĨħ
    -0.19
    æ²Ķ
    -0.18
    POSITIVE LOGITS
    ually
    0.20
    å©ļ姻
    0.19
     institutions
    0.19
     institution
    0.18
    istically
    0.18
    isti
    0.18
    KI
    0.18
    ä½ľçĶ¨
    0.17
    estruct
    0.17
     marriage
    0.17
    Activations Density 0.006%

    No Known Activations