© 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. 10859
    Prev
    Next
    INDEX
    Explanations

    founder of modern

    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
    ç¥ī
    -0.20
     unlink
    -0.19
    éľĢè¦ģçĶ¨åĪ°
    -0.19
     ResourceManager
    -0.18
    符åIJĪæĿ¡ä»¶
    -0.18
    éĻĦåĬł
    -0.18
     Huff
    -0.17
     ÑģпеÑĨиалÑĮно
    -0.17
    é¡¹çĽ®çļĦ
    -0.17
    ilon
    -0.17
    POSITIVE LOGITS
    å¼ĢåĪĽ
    0.26
    å¥łå®ļäºĨ
    0.24
    é¢ĨåħĪ
    0.24
    å¥łå®ļ
    0.22
     seminal
    0.22
    çĪ·
    0.20
    æĹ©æľŁ
    0.20
    æıIJæĹ©
    0.20
     landmarks
    0.20
    é¢ĨåħĪåľ°ä½į
    0.20
    Activations Density 0.085%

    No Known Activations