© 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. 10346
    Prev
    Next
    INDEX
    Explanations

    licorice

    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´¸
    -0.20
    æĤ´
    -0.19
    ä¾Ī
    -0.19
    åĨ·æ¼ł
    -0.19
    Blo
    -0.18
    éĵĿåIJĪéĩij
    -0.18
    éĴĹ
    -0.18
     Cree
    -0.18
    俯
    -0.18
    osaur
    -0.18
    POSITIVE LOGITS
    ipping
    0.20
    pants
    0.19
     lik
    0.18
    0.18
    ISCO
    0.18
    dra
    0.18
    è¢ħ
    0.18
    ãģı
    0.17
    isco
    0.17
    igma
    0.17
    Activations Density 0.003%

    No Known Activations