© 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. 11570
    Prev
    Next
    INDEX
    Explanations

    legal citations and structure

    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
    -0.20
    ivos
    -0.19
    -0.18
    ä»Ģ
    -0.17
    ราà¸Ĭ
    -0.17
    ç©´
    -0.17
    vo
    -0.17
    à¸Ļาม
    -0.17
    åĶ¯ä¸Ģ
    -0.17
    æ¶ĪèĢĹ
    -0.16
    POSITIVE LOGITS
    åıªè§ģ
    0.19
    ç¿©
    0.18
    Powered
    0.17
     McCart
    0.17
    æºī
    0.17
    è¯Ŀ说
    0.17
    é£ŀ
    0.17
    Americ
    0.17
    çīĪæĿĥ声æĺİ
    0.17
     Fukushima
    0.17
    Activations Density 0.039%

    No Known Activations