© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15216
    Prev
    Next
    INDEX
    Explanations

    is a

    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
     ÑĢÑĥков
    -0.29
    ä¸īç§įèģĮä¸ļ
    -0.27
    åľ¨çݩ家ä¸Ń
    -0.26
    åįķèģĮä¸ļ
    -0.26
     ÐIJлекÑģан
    -0.25
     ÐŁÐ¾Ñĩем
    -0.25
    ÑģоÑĨиалÑĮн
    -0.24
     педаг
    -0.24
    wyż
    -0.23
    ÑĩÑĢежден
    -0.23
    POSITIVE LOGITS
    çĭ¬çī¹çļĦ
    0.32
    ç¾İæĻ¯
    0.31
    åı¤èĢģ
    0.29
    æĻ¯èī²
    0.29
    å½ĵåľ°äºº
    0.28
    æĤłä¹ħ
    0.28
    æĸĩåĮĸåºķèķ´
    0.28
    æľĢç¾İçļĦ
    0.28
    çĭ¬çī¹
    0.27
    丰å¯ĮçļĦ
    0.27
    Activations Density 0.144%

    No Known Activations