© 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. 17263
    Prev
    Next
    INDEX
    Explanations

    well hung guys

    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
    è£Ļ
    -0.20
    è£ĻåŃIJ
    -0.20
    attern
    -0.20
    npos
    -0.19
    沿
    -0.19
    .df
    -0.18
     resil
    -0.18
    æķŀ
    -0.18
    èĤ©èĨĢ
    -0.18
    è°ĥçļ®
    -0.18
    POSITIVE LOGITS
    é«ĺæ¸ħ
    0.22
    éķ¦
    0.21
    æĮĩ导ä¸ĭ
    0.19
    ç²¾åŃIJ
    0.19
     erection
    0.19
    èĦĪ
    0.19
    Synopsis
    0.19
    浡
    0.18
     Trucks
    0.18
     Penis
    0.18
    Activations Density 0.019%

    No Known Activations