© 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. 10688
    Prev
    Next
    INDEX
    Explanations

    Scientology and astrology

    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
    agr
    -0.20
    Lng
    -0.20
    aned
    -0.20
     Brooks
    -0.19
    ((&
    -0.18
    带éĺŁ
    -0.18
    sse
    -0.18
    éĤ£ä¹Ī容æĺĵ
    -0.18
    èĩªä¸»
    -0.17
    udu
    -0.17
    POSITIVE LOGITS
    åĪĽå§ĭ人
    0.21
     Scientology
    0.20
    åIJĪæ³ķ
    0.19
    yon
    0.18
    æ³ķåĪ¶
    0.18
    -linked
    0.18
    å¦Ĩ
    0.18
     controversial
    0.17
    /ph
    0.17
    /Y
    0.17
    Activations Density 0.002%

    No Known Activations