© 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. 16444
    Prev
    Next
    INDEX
    Explanations

    resource development and land use

    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
    æIJª
    -0.21
    çĭ¡
    -0.20
    éĤ£ä»½
    -0.20
    ยà¸Ńà¸Ķ
    -0.20
    æĪĺåıĭ
    -0.19
    ä¸Ģé¢Ĺ
    -0.19
    ä¸įä½İäºİ
    -0.19
    æŶéĹ´èĬĤçĤ¹
    -0.19
    åºŁè¯Ŀ
    -0.18
    大åĴĸ
    -0.18
    POSITIVE LOGITS
    ç§ģ
    0.21
    çŃīæ´»åĬ¨
    0.21
     Justi
    0.21
    åĪº
    0.20
     invasive
    0.20
    å¹²é¢Ħ
    0.20
    å¹²æī°
    0.19
    çļĦå½±åĵį
    0.19
     absentee
    0.19
     private
    0.19
    Activations Density 0.057%

    No Known Activations