© 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. 15888
    Prev
    Next
    INDEX
    Explanations

    articles, studies, or medical reports

    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
    è¿Ļæīįæĺ¯
    -0.24
    è¿Ļæĺ¯æĪij们
    -0.23
    è¿Ļå°±æĺ¯
    -0.22
    è¿Ļæĺ¯ä¸Ģç§į
    -0.21
     Turns
    -0.21
    è¿Ļæĺ¯
    -0.20
    åħ¶å®ŀå°±æĺ¯
    -0.19
    æĪĸèĢħæĺ¯
    -0.19
    è¿Ļåıªæĺ¯
    -0.19
     limburg
    -0.18
    POSITIVE LOGITS
    åĽłåħ¶
    0.22
    æľ¬æĬ¥è®¯
    0.20
    odel
    0.19
    asley
    0.19
    Æ°á»Ŀng
    0.19
    éĿ¢ä¸´çĿĢ
    0.19
    为åħ¶
    0.18
    uy
    0.18
    bers
    0.18
    çļĦä¸Ģ项
    0.18
    Activations Density 0.448%

    No Known Activations