© 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. 13709
    Prev
    Next
    INDEX
    Explanations

    health statistics or percentages

    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
    äºĨ许å¤ļ
    -0.24
    ä¸ĢåĪĩéĥ½
    -0.23
    äºĨå¾Īå¤ļ
    -0.22
    äºĨ好å¤ļ
    -0.21
    ä¹Łæĺ¯ä¸Ģç§į
    -0.21
    æľīæŶ
    -0.21
    å¾Īå¤ļäºĭæĥħ
    -0.21
    äºĨå¾Īä¹ħ
    -0.20
    æľīæŶåĢĻ
    -0.20
    äºĨä¸ĢäºĽ
    -0.20
    POSITIVE LOGITS
    ä¸įåIJĮç¨ĭ度
    0.37
    ê±°ëĤĺ
    0.23
    èĩ³å°ij
    0.23
     themselves
    0.20
    å¹³åĿĩæ¯ı
    0.20
     either
    0.20
    æĦıä¹īä¸ĬçļĦ
    0.19
     alguna
    0.19
    their
    0.19
     their
    0.19
    Activations Density 0.244%

    No Known Activations