© 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. 10810
    Prev
    Next
    INDEX
    Explanations

    letters picked, third derivative

    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
    åıªæĺ¯ä¸ºäºĨ
    -0.21
    çļĦ身ä½ĵ
    -0.21
    .pattern
    -0.19
    被æįķ
    -0.18
    ä¸Ģæŀ¶
    -0.18
    èµĿ
    -0.18
    æĸĩåĮĸåĴĮ
    -0.17
    è¿Ļ个èģĮä¸ļ
    -0.17
    capture
    -0.17
    ä»ĭ
    -0.17
    POSITIVE LOGITS
    æĭį
    0.22
    itar
    0.21
    ç«Ł
    0.21
     Vulcan
    0.20
    illard
    0.19
    ắc
    0.19
    grpc
    0.19
    림
    0.19
    åİ»æİī
    0.19
    	strcat
    0.18
    Activations Density 0.006%

    No Known Activations