© 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. 15091
    Prev
    Next
    INDEX
    Explanations

    visitors to places

    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±¢
    -0.20
    æIJ¬å®¶
    -0.20
    èĽ±
    -0.19
    æ¯ĴæĢ§
    -0.18
    å°ıå¾®
    -0.18
    ä¸ŃæľŁ
    -0.18
    档次
    -0.18
    æľ¬äºº
    -0.18
    大åıĶ
    -0.18
    .calls
    -0.17
    POSITIVE LOGITS
    åıĤè§Ĥ
    0.25
     visitors
    0.25
    è·¯è¿ĩ
    0.24
    æĿ¥è®¿
    0.22
    -Za
    0.21
    æĩĭ
    0.21
    è¿ĽæĿ¥
    0.21
    èĢħ
    0.21
    人次
    0.20
    åĵ¡
    0.20
    Activations Density 0.034%

    No Known Activations