© 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. 16582
    Prev
    Next
    INDEX
    Explanations

    recurring payments or intervals

    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
    truth
    -0.21
    ConfigurationException
    -0.20
    è£ģåijĺ
    -0.19
    çijķ
    -0.19
    athom
    -0.19
    side
    -0.18
    ,,,
    -0.18
     colspan
    -0.18
     hl
    -0.18
    伪éĢł
    -0.18
    POSITIVE LOGITS
    å®ļæľŁ
    0.27
    åĽºå®ļçļĦ
    0.26
     monthly
    0.25
    稳å®ļçļĦ
    0.24
    æ¯ıæľĪ
    0.24
    档次
    0.22
    æºIJæºIJä¸įæĸŃ
    0.22
    è¿ŀç»Ń
    0.22
    Regular
    0.22
    éģĩ
    0.22
    Activations Density 0.041%

    No Known Activations