© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15739
    Prev
    Next
    INDEX
    Explanations

    acid, ceph, bif, igmat, idal

    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
    antan
    -0.20
    sWith
    -0.19
    èIJ¥ä¸ļé¢Ŀ
    -0.19
    tran
    -0.19
    åľ°éģĵ
    -0.19
    éŃĶ
    -0.19
     tranny
    -0.18
    istically
    -0.18
    éŃĶçİĭ
    -0.18
    Magic
    -0.18
    POSITIVE LOGITS
    .lift
    0.21
     Ernst
    0.19
    æľ¬ç½ij
    0.19
    æĥ³å¿µ
    0.18
    åIJį人
    0.18
    ugged
    0.18
     Healthy
    0.18
    诸èijĽ
    0.18
    .resume
    0.17
     Tokyo
    0.17
    Activations Density 0.003%

    No Known Activations