© 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. 17060
    Prev
    Next
    INDEX
    Explanations

    Elizabeth Warren / protection / drug administration

    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
    ledge
    -0.23
    åģĩåĨĴ
    -0.20
    çİĭåºľ
    -0.19
    ArrayOf
    -0.19
    å£ij
    -0.19
    çĽij
    -0.18
    çģµåĬ¨
    -0.18
    gain
    -0.18
    ECH
    -0.18
    publisher
    -0.18
    POSITIVE LOGITS
    iland
    0.23
    èĬĴ
    0.23
     celib
    0.21
    åĩºäºĨ
    0.19
    润æ»ij
    0.19
    onnen
    0.19
     Bundes
    0.18
    轸
    0.18
    éĵ©
    0.18
    ener
    0.17
    Activations Density 0.004%

    No Known Activations