© 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. 17287
    Prev
    Next
    INDEX
    Explanations

    works at

    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
    å¤ĩ
    -0.21
    åĪĴ
    -0.20
    é©·
    -0.19
     coll
    -0.19
    uze
    -0.18
    orry
    -0.18
    (let
    -0.18
    ä¸ĵçĶ¨
    -0.18
    _dispatcher
    -0.18
    æħķ
    -0.18
    POSITIVE LOGITS
    tru
    0.23
    庵
    0.18
    ç¬ij声
    0.18
    cmb
    0.18
     Faculty
    0.18
     Mills
    0.18
    æıī
    0.17
    IST
    0.17
    Faculty
    0.17
    ä¸Ģç»Ħ
    0.17
    Activations Density 0.029%

    No Known Activations