© 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. 13752
    Prev
    Next
    INDEX
    Explanations

    Red Hat

    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
    绵éĺ³
    -0.25
    涪
    -0.24
    æ¹ĺ西
    -0.23
    åĽĽå·Ŀçľģ
    -0.23
    å¼łå®¶åı£
    -0.22
    åĨ¬å¥¥
    -0.22
    涿
    -0.21
    çīĤ
    -0.20
    èľĢ
    -0.20
    åĿ¨
    -0.20
    POSITIVE LOGITS
    èĮĤåIJį
    0.26
    举èIJ¥
    0.24
    太æ¹ĸ
    0.23
    èĬĿåĬłåĵ¥
    0.23
    宿è¿ģ
    0.23
    æŀķ
    0.23
    临æ²Ĥ
    0.22
    (GTK
    0.22
     Chicago
    0.22
     Croatian
    0.22
    Activations Density 0.246%

    No Known Activations