© 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. 15856
    Prev
    Next
    INDEX
    Explanations

    health significance

    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
    icter
    -0.20
    putc
    -0.19
    èİ©
    -0.18
    廪
    -0.18
    ä¹Łæĺ¯ä¸Ģ个
    -0.18
    ä¸Ģäºĭ
    -0.18
    edata
    -0.18
    æĺ¯ä¸Ģ件
    -0.17
    笪
    -0.17
    æ¾ī
    -0.17
    POSITIVE LOGITS
     familiar
    0.29
    çĨŁæĤīçļĦ
    0.28
    çĨŁæĤī
    0.24
    常è§ģçļĦ
    0.23
    iez
    0.23
    æŃ£å¸¸ä½¿çĶ¨
    0.22
    æĹ¥å¸¸
    0.22
     Bias
    0.21
    bias
    0.21
    åİ¢
    0.21
    Activations Density 0.113%

    No Known Activations