© 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. 10679
    Prev
    Next
    INDEX
    Explanations

    GAME Free SLOT MACHINES

    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
    æī«ä¸Ģæī«
    -0.20
    ÏĬ
    -0.19
     оÑĩеÑĢ
    -0.19
    Lord
    -0.18
    åı¸ä»¤
    -0.18
    æ¯ĶæĪij
    -0.16
    èĤ¯å®ļ
    -0.16
     heed
    -0.16
    å¾Ģåīį
    -0.16
    න
    -0.16
    POSITIVE LOGITS
    æļ¨
    0.18
     ·
    0.17
     Ru
    0.17
    æĪIJ为ä¸ŃåĽ½
    0.17
    å¥¹åľ¨
    0.17
     Gra
    0.16
    æ®ī
    0.16
     Cro
    0.16
    éĺħ读åħ¨æĸĩ
    0.16
    RAP
    0.16
    Activations Density 0.119%

    No Known Activations