© 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. 11971
    Prev
    Next
    INDEX
    Explanations

    component names

    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
    ä¸įæĪIJ
    -0.24
    责任åĪ¶
    -0.22
    aken
    -0.22
    deque
    -0.21
    èĹģ
    -0.19
    æºIJæºIJ
    -0.19
    é£ĺ
    -0.19
    Err
    -0.18
     Neh
    -0.18
    å¢ĻéĿ¢
    -0.18
    POSITIVE LOGITS
    åĵģçīĮ
    0.23
    åıĬ缸åħ³
    0.22
    éĢĤåIJĪ
    0.21
    设计
    0.20
    åĵģçīĮçļĦ
    0.20
    egin
    0.20
    éĩĩçĶ¨äºĨ
    0.19
    ä¸ĸ家
    0.19
    å¤ļå°ijéĴ±
    0.19
    æľĢéĢĤåIJĪ
    0.19
    Activations Density 0.174%

    No Known Activations