© 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. 11481
    Prev
    Next
    INDEX
    Explanations

    future events or outcomes

    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
    è¿ijå¹´æĿ¥
    -0.21
    åİĨæĿ¥
    -0.19
    ãģĭãģ¤
    -0.19
    å½ĵå¹´
    -0.18
    好ä¸į容æĺĵ
    -0.18
    éĻŁ
    -0.18
    ä»İæĿ¥
    -0.18
    å¼ĢéŨ
    -0.17
    åİĨåı²æĤłä¹ħ
    -0.17
    è¿Ļä¹Īå¤ļå¹´
    -0.17
    POSITIVE LOGITS
    soon
    0.22
    åĩĨ
    0.20
    æľªæĿ¥çļĦ
    0.20
     новÑĭе
    0.20
    åıĸå¾Ĺ以åıĬ
    0.19
    ElementException
    0.19
     soon
    0.19
    寡
    0.18
     future
    0.18
    éĺ¡
    0.18
    Activations Density 0.027%

    No Known Activations