© 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. 17308
    Prev
    Next
    INDEX
    Explanations

    continue reading

    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
    ween
    -0.21
    ä¸İåIJ¦
    -0.20
     unders
    -0.19
    library
    -0.19
    æī§ä¸ļ
    -0.19
    åĩĨæŶ
    -0.18
    леж
    -0.18
    sgi
    -0.18
    unders
    -0.18
    离
    -0.18
    POSITIVE LOGITS
    .Fat
    0.20
     Conway
    0.19
    家åĽŃ
    0.18
    åĪ°æĿ¥
    0.18
    bish
    0.18
    å¤Ń
    0.17
     Cousins
    0.17
    æĢĿ
    0.17
     ck
    0.17
    å¸ĥ
    0.17
    Activations Density 0.005%

    No Known Activations