© 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. 11091
    Prev
    Next
    INDEX
    Explanations

    crate of grain, sand, linen, log, ore, clothes

    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
    æ¦Ħ
    -0.22
    强
    -0.21
    åīįåIJİ
    -0.20
    äºĭçī©
    -0.20
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.20
    æľīæīĢ
    -0.19
     mer
    -0.19
    æĥħ趣
    -0.19
    åģļäºĭ
    -0.18
    uma
    -0.18
    POSITIVE LOGITS
    ä¾ĽåºĶ
    0.26
    æĿ¥èĩª
    0.24
    éĢģåĪ°
    0.24
    çļĦæķ°éĩı
    0.23
    åįĸç»Ļ
    0.23
     اÙĦخاÙħ
    0.22
    åŃĺåĤ¨
    0.22
    ä¾Ĩèĩª
    0.22
    crate
    0.22
    è¿IJè¾ĵ
    0.22
    Activations Density 0.146%

    No Known Activations