© 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. 11621
    Prev
    Next
    INDEX
    Explanations

    antibiotics and animal growth promotion

    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
    åĬ©æĶ»
    -0.25
     Blitz
    -0.22
     ero
    -0.20
    大èĩªçĦ¶
    -0.20
    çİĭæľĿ
    -0.19
    ORB
    -0.19
    çIJĨå·¥
    -0.19
    强æľīåĬĽçļĦ
    -0.18
    覽
    -0.18
    æѦæŀĹ
    -0.18
    POSITIVE LOGITS
    auge
    0.20
    é¦
    0.20
     im
    0.19
    frei
    0.19
    metic
    0.19
    çĮªèĤī
    0.19
    饲
    0.19
    uling
    0.19
     feeding
    0.19
    ivery
    0.18
    Activations Density 0.024%

    No Known Activations