© 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. 10390
    Prev
    Next
    INDEX
    Explanations

    legal citations

    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
     unheard
    -0.23
    end
    -0.21
    DOWNLOAD
    -0.19
    è¿Ļç§įæĥħåĨµ
    -0.19
    éĥ½åĸľæ¬¢
    -0.19
    oz
    -0.19
    åĽºçĦ¶
    -0.18
    ä½Ĩæĺ¯ä»ĸ
    -0.18
    hi
    -0.18
    ces
    -0.18
    POSITIVE LOGITS
    åIJįæł¡
    0.21
    ~":"
    0.19
    ðŁĺ¥
    0.19
    uentes
    0.19
    碰æĴŀ
    0.18
    çķĻ
    0.18
     ;;=
    0.18
    ðŁĺŀ
    0.18
    ucene
    0.18
    èµĦæºIJéħįç½®
    0.18
    Activations Density 0.069%

    No Known Activations