© 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. 16996
    Prev
    Next
    INDEX
    Explanations

    viruses

    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
    éĶĿ
    -0.24
    rats
    -0.20
    uft
    -0.19
     LSTM
    -0.19
    è¿Ļå¥Ĺ
    -0.18
    zew
    -0.18
    离å¼ĢäºĨ
    -0.18
    ÙĦاÙĦ
    -0.18
    erland
    -0.18
     RAT
    -0.18
    POSITIVE LOGITS
     FOUND
    0.21
     hyp
    0.21
    大åŀĭ
    0.20
     dio
    0.19
    æļĸ
    0.19
    äºĭ件
    0.19
    /Foundation
    0.19
     hypers
    0.18
     family
    0.18
    егиÑģÑĤ
    0.18
    Activations Density 0.087%

    No Known Activations