© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15332
    Prev
    Next
    INDEX
    Explanations

    due to or caused by

    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
    顺
    -0.21
    顶
    -0.21
    	TokenName
    -0.18
    аÑĢа
    -0.17
    å²ŃåįĹ
    -0.17
    è´¿
    -0.17
    èĥ¸åīį
    -0.17
     ÑģÑĢазÑĥ
    -0.17
     Psychiat
    -0.17
     brink
    -0.17
    POSITIVE LOGITS
     either
    0.22
     previous
    0.22
    é£İåIJ¹
    0.21
    ä»Ģä¹ĪåİŁåĽł
    0.21
    æĿ¥èĩªäºİ
    0.21
     various
    0.21
    à¸Īาà¸ģà¸ģาร
    0.20
    eva
    0.20
    either
    0.20
    è¦ģä¹Ī
    0.19
    Activations Density 0.191%

    No Known Activations