© 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. 10333
    Prev
    Next
    INDEX
    Explanations

    preced-ence

    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
    çıī
    -0.19
    çĶŁåŃĺ
    -0.19
    æ¯ķ
    -0.19
    éĶµ
    -0.18
    BOX
    -0.17
    è¶ħé«ĺ
    -0.17
    èµŁ
    -0.17
     Mattis
    -0.17
    POR
    -0.17
     garage
    -0.17
    POSITIVE LOGITS
    çķ´
    0.20
    é£İåħī
    0.19
    ÙĨÙĥ
    0.19
    纹
    0.18
    å©ļ
    0.18
    éħ
    0.18
    æĹħ游度åģĩ
    0.17
    éĺ²çĽĹ
    0.17
     tac
    0.17
    leaning
    0.17
    Activations Density 0.405%

    No Known Activations