© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15144
    Prev
    Next
    INDEX
    Explanations

    corporate business events

    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
    æĬ¥ä¸ļ
    -0.22
    abay
    -0.21
    å¯Ŀ
    -0.20
    å¬ĸ
    -0.20
    AndGet
    -0.19
    /il
    -0.19
    åīįéĶĭ
    -0.19
    ä½ľåĿĬ
    -0.18
     пÑĢид
    -0.18
    Ahead
    -0.18
    POSITIVE LOGITS
    åĬŀåħ¬
    0.32
    çĻ½é¢Ĩ
    0.32
     corporate
    0.31
    èģĮåľº
    0.28
     office
    0.28
    åĨĻåŃĹ楼
    0.25
    人士
    0.25
    楼å®ĩ
    0.25
    åĬŀåħ¬å®¤
    0.25
    ä¸Ĭåı¸
    0.24
    Activations Density 0.080%

    No Known Activations