© 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. 10547
    Prev
    Next
    INDEX
    Explanations

    cum followed by other words

    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
     Politico
    -0.20
    åijĭ
    -0.19
    æĿ¥èĩªäºİ
    -0.18
    æķ£
    -0.18
    æĻļé¥Ń
    -0.18
    æ´Ĺå¹²åĩĢ
    -0.18
    æ»ļæ»ļ
    -0.18
    ĥģ
    -0.17
    åĪ»çĶ»
    -0.17
    POST
    -0.17
    POSITIVE LOGITS
    ene
    0.20
    unter
    0.20
    èį£èªī
    0.19
    ich
    0.19
    åºĶæľīçļĦ
    0.19
    uros
    0.19
    ../../
    0.18
    ersen
    0.18
    uan
    0.18
    ÑĥÑĤ
    0.18
    Activations Density 0.002%

    No Known Activations