© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14017
    Prev
    Next
    INDEX
    Explanations

    medical and technical terms

    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
    ocom
    -0.20
    unch
    -0.20
    ail
    -0.20
    ****
    -0.18
    ace
    -0.18
    ä¸į管æĺ¯
    -0.18
    ÑģÑĤи
    -0.17
    umbo
    -0.17
    ando
    -0.17
    ä¸įèĩ³äºİ
    -0.17
    POSITIVE LOGITS
    æľīä½ķ
    0.27
    æľīä»Ģä¹Ī
    0.24
    æľīåĵªäºĽ
    0.21
     vs
    0.21
    ç«Łæĺ¯
    0.20
    éģŃ
    0.19
    å´©æºĥ
    0.19
    ãģ«ãģĬãģijãĤĭ
    0.19
    æľīå¤ļå°ij
    0.19
    è°ĥæŁ¥æĺ¾ç¤º
    0.19
    Activations Density 0.761%

    No Known Activations