© 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. 12137
    Prev
    Next
    INDEX
    Explanations

    1970s nostalgia

    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
    èģĶåIJĪä¼ļ
    -0.22
    å¾Ĺèµ·
    -0.21
    igner
    -0.20
    è´¯
    -0.19
    åĬ¼
    -0.19
    çĤĺ
    -0.19
    åij¨ä¸Ģ
    -0.19
    erals
    -0.18
    æĸ¯å¡Ķ
    -0.18
    tings
    -0.18
    POSITIVE LOGITS
    Unix
    0.18
    éĹ¯
    0.18
     Unix
    0.18
    alance
    0.17
    åıªæĺ¯ä¸ºäºĨ
    0.17
    éĶĢåĶ®æĶ¶åħ¥
    0.17
    æĽĻåħī
    0.17
    æĶ¿
    0.17
    è¿Ń
    0.17
    éĴĿ
    0.17
    Activations Density 0.219%

    No Known Activations