© 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. 15936
    Prev
    Next
    INDEX
    Explanations

    United States elections

    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
    管çIJĨ模å¼ı
    -0.20
    åľ¨åĽ½å¤ĸ
    -0.19
    éŁ³åĵį
    -0.19
    èĬ±èįī
    -0.18
    è¿Ļ个è¡Įä¸ļ
    -0.18
    ÙĨØ´
    -0.18
    _REPLY
    -0.18
     thumbnail
    -0.18
    åıĮèĦļ
    -0.17
    èĩªèº«çļĦ
    -0.17
    POSITIVE LOGITS
    两次
    0.24
    æĥħå½¢
    0.21
    å½ĵéĢī
    0.21
    пÑĢоÑĦеÑģÑģионал
    0.20
    ä¸ī次
    0.20
    迳
    0.20
    itzer
    0.20
    _ComCallableWrapper
    0.20
     пÑĢиÑıÑĤн
    0.20
    itz
    0.19
    Activations Density 0.036%

    No Known Activations