© 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. 17062
    Prev
    Next
    INDEX
    Explanations

    specific goals

    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
    íĹĢ
    -0.32
    ÓĽ
    -0.30
    ÑĩÑĢежден
    -0.26
    еÑģÑĤеÑģÑĤвенн
    -0.24
    ÑĢеги
    -0.24
     ÐIJлекÑģан
    -0.24
    наÑĨионалÑĮн
    -0.24
    æľĢçĪ±
    -0.23
    ãģ£ãģ¡ãĤĥ
    -0.23
    ç¦ģ
    -0.23
    POSITIVE LOGITS
     zwy
    0.29
    æĪĸå¤ļæĪĸå°ij
    0.29
    éĢļ常æĺ¯
    0.28
    èĵĵ
    0.26
    æŁIJç§į
    0.26
    æŁIJä¸Ģ
    0.25
     usually
    0.25
     или
    0.25
     atau
    0.24
     ëĺIJëĬĶ
    0.24
    Activations Density 1.289%

    No Known Activations