© 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. 11539
    Prev
    Next
    INDEX
    Explanations

    a/an followed by noun

    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
     guy
    -0.20
    åij³
    -0.19
    ç³»ç»ŁçļĦ
    -0.19
    æĸĩåĮĸçļĦ
    -0.19
    αι
    -0.18
     gust
    -0.18
    arena
    -0.17
    人æŃ»äº¡
    -0.17
     unstable
    -0.17
    ä¸Ģåľº
    -0.17
    POSITIVE LOGITS
    æĬµè¾¾
    0.22
    åīįä¸ī
    0.20
    ä¸ī级
    0.19
    uario
    0.19
    çĶŁæķĪ
    0.19
    æıIJæ¡Ī
    0.19
     QPoint
    0.19
    çķĻåѦçĶŁ
    0.18
    inho
    0.18
    é¾Ħ
    0.18
    Activations Density 0.014%

    No Known Activations