© 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. 11069
    Prev
    Next
    INDEX
    Explanations

    synthase, oxidase, dehydrogenases

    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
    èł²
    -0.24
    èĿĮ
    -0.20
    家åĬ¡
    -0.19
    æĢģ
    -0.19
    âĩIJ
    -0.18
    çĨĦ
    -0.18
    çŁŃæľŁåĨħ
    -0.18
    ONY
    -0.18
    اÙħر
    -0.18
    é¹Ĭ
    -0.18
    POSITIVE LOGITS
    æİ¥åĬĽ
    0.21
    åıī
    0.20
    lund
    0.18
    åħ¥åĽ´
    0.18
    éģİç¨ĭ
    0.18
    æĮ¤
    0.18
    寥
    0.18
    ä¹³æĪ¿
    0.18
    AndGet
    0.17
    éĥ¢
    0.17
    Activations Density 0.251%

    No Known Activations