© 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. 17194
    Prev
    Next
    INDEX
    Explanations

    deep learning

    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
     Alps
    -0.20
     deeply
    -0.18
     deeper
    -0.18
    esthetic
    -0.18
    深深çļĦ
    -0.17
    ikan
    -0.16
    æ·±æ·±åľ°
    -0.16
    åĽ°æĥij
    -0.16
    深度
    -0.16
    haft
    -0.16
    POSITIVE LOGITS
    ened
    0.21
    ening
    0.20
    ify
    0.19
    ing
    0.19
    aÄŁa
    0.18
    eners
    0.18
    éªĭ
    0.18
    à¹Ĩ
    0.17
    ness
    0.17
    ifying
    0.17
    Activations Density 0.011%

    No Known Activations