© 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. 14197
    Prev
    Next
    INDEX
    Explanations

    high purity and quality

    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
    ocre
    -0.21
     Ñĥни
    -0.21
    ãģĹãģŁãģĵãģ¨
    -0.20
    年人
    -0.20
    hol
    -0.19
    æĮ¨
    -0.19
    æµij身
    -0.19
    inear
    -0.19
    ä¼ļè§īå¾Ĺ
    -0.19
    bum
    -0.18
    POSITIVE LOGITS
    åĵģè´¨
    0.28
     quality
    0.26
    æĿĤè´¨
    0.24
     standards
    0.24
    产åĵģ
    0.23
    quality
    0.23
    è´¨éĩıåĴĮ
    0.23
    åĵģ質
    0.23
    精度
    0.23
    -quality
    0.22
    Activations Density 0.054%

    No Known Activations