© 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. 10667
    Prev
    Next
    INDEX
    Explanations

    doi, https, abstract links

    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
    Not in Any Lists

    No Comments

    Negative Logits
     stumbling
    -0.20
    enty
    -0.18
    .hd
    -0.18
    éĢĢ
    -0.18
     ease
    -0.18
    åı¥
    -0.17
    ots
    -0.17
    ä¸įèĩ³äºİ
    -0.17
    restart
    -0.17
    æij¸
    -0.17
    POSITIVE LOGITS
    夫å¦ĩ
    0.22
    ç´«å¤ĸ线
    0.21
    æijĺè¦ģ
    0.20
    èĴŁ
    0.20
    æĴ°åĨĻ
    0.20
    使çĶ¨èĢħæĪĸ
    0.20
    EIF
    0.20
    åħ±åĪĽ
    0.19
    纸ä¸Ĭ
    0.19
    è¿Ļ个人
    0.19
    Activations Density 0.056%

    No Known Activations