© 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. 15328
    Prev
    Next
    INDEX
    Explanations

    applications and content creation

    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
    éĢĤå½ĵçļĦ
    -0.23
    æĮ¡ä½ı
    -0.21
    åĽºå®ļçļĦ
    -0.20
    宫
    -0.20
    ksen
    -0.19
    æľīæķĪåľ°
    -0.19
    æ¡£
    -0.19
    å°±æĺ¯åĽłä¸º
    -0.18
    æľīæķĪçļĦ
    -0.18
    åijĹ
    -0.18
    POSITIVE LOGITS
    åĭ¿
    0.23
     germ
    0.20
    æ³ī
    0.20
    伤亡
    0.19
    æģķ
    0.18
     entertain
    0.18
    arness
    0.18
    å¹½é»ĺ
    0.18
    娱
    0.17
    伤
    0.17
    Activations Density 0.043%

    No Known Activations