© 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. 11427
    Prev
    Next
    INDEX
    Explanations

    Stakes race horse event

    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
    .visit
    -0.19
    çļĦæĪ¿åŃIJ
    -0.19
    .crm
    -0.18
    è°®
    -0.18
    æį½
    -0.18
     Baylor
    -0.18
    raphics
    -0.18
    obao
    -0.18
    جز
    -0.17
    éĵĦ
    -0.17
    POSITIVE LOGITS
    æĹ¶æ®µ
    0.25
    ä¸įåĪĨ
    0.24
    åĪĽæĸ°é©±åĬ¨
    0.23
    æ¿ĢçĥĪçļĦ
    0.22
    åħ¨åľº
    0.22
    ponsored
    0.21
    éĥ¨ä¸»ä»»
    0.20
    èIJ¥ä¸ļ
    0.20
    æĺİ天
    0.20
    è§Ħæł¼
    0.19
    Activations Density 0.029%

    No Known Activations