© 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. 17112
    Prev
    Next
    INDEX
    Explanations

    register today online for form at website

    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
    ogn
    -0.20
    çݦ
    -0.19
    anye
    -0.19
    çķĻè¨ĢæĿ¿
    -0.18
    åĽłåľ°
    -0.18
    污æŁĵ
    -0.18
    nid
    -0.17
    ä¸ĸ家
    -0.17
    /rss
    -0.17
    èĢģ人家
    -0.17
    POSITIVE LOGITS
    æĬ¥åIJį
    0.24
    éłIJ
    0.21
    表
    0.20
    缼
    0.20
    é¢Ħ
    0.20
    BuilderFactory
    0.19
    èĩªçIJĨ
    0.19
    _centers
    0.19
    è´¹çĶ¨
    0.19
    INGER
    0.18
    Activations Density 0.007%

    No Known Activations