© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16964
    Prev
    Next
    INDEX
    Explanations

    veterinary medicine and animals

    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
     uncle
    -0.21
    éħ¿
    -0.20
    太æŀģ
    -0.20
    æĮ¥
    -0.20
    åİŁæ²¹
    -0.20
    ä¸ĭãģĴ
    -0.20
    æļĹæļĹ
    -0.19
    Measured
    -0.19
    tml
    -0.18
    otton
    -0.18
    POSITIVE LOGITS
    çĬ¬
    0.34
    åħ½
    0.30
     veterin
    0.25
    çį¸
    0.23
    ä¸ĵä¸ļåĮĸ
    0.22
    主人
    0.22
    饲
    0.21
    iếc
    0.21
     ÑģлÑĥÑĩ
    0.20
    å®łçī©
    0.20
    Activations Density 0.032%

    No Known Activations