© 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. 10433
    Prev
    Next
    INDEX
    Explanations

    numbers and statistics

    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
    鼶è·Ŀ离
    -0.20
    åĪº
    -0.20
    PIO
    -0.20
    IDX
    -0.19
    诰
    -0.18
    åıĮåIJij
    -0.18
     maxx
    -0.18
     Alias
    -0.18
    ÑĿ
    -0.18
     zak
    -0.17
    POSITIVE LOGITS
    kowski
    0.20
    лÑı
    0.19
    èģĴ
    0.18
    æī§æĦı
    0.18
    inue
    0.18
    ues
    0.18
    ucked
    0.17
    ueue
    0.17
    åĹĵ
    0.17
    exp
    0.17
    Activations Density 0.157%

    No Known Activations