© 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. 10322
    Prev
    Next
    INDEX
    Explanations

    merging, fusion, convergence

    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
    Negative Logits
    azers
    -0.21
    屿
    -0.21
    泡
    -0.18
    éĢłçº¸
    -0.18
    å±¥
    -0.18
    actable
    -0.18
    tober
    -0.17
    irie
    -0.17
    screen
    -0.17
    ysi
    -0.17
    POSITIVE LOGITS
    åľ¨ä¸Ģèµ·
    0.39
     between
    0.37
     междÑĥ
    0.36
    between
    0.32
    线ä¸Ĭ线ä¸ĭ
    0.31
     بÙĬÙĨ
    0.31
    .merge
    0.29
     Between
    0.28
     zwischen
    0.28
    èŀįåIJĪ
    0.28
    Activations Density 0.365%

    No Known Activations