© 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. 15148
    Prev
    Next
    INDEX
    Explanations

    agents or owners

    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
    罩
    -0.22
    é¢ĨåĨĽ
    -0.20
    -txt
    -0.19
    æĽ´å¼º
    -0.18
     hunter
    -0.18
     viewers
    -0.18
    è§Ĥä¼Ĺ
    -0.18
    åı£å¾Ħ
    -0.18
    æĪ³
    -0.18
     Fucked
    -0.17
    POSITIVE LOGITS
    åĩºè®©
    0.26
    åİŁ
    0.24
    åįĸç»Ļ
    0.24
    转让
    0.23
    åī©ä½Ļ
    0.23
    orra
    0.22
    åij¨è½¬
    0.21
    åĩºéģĵ
    0.21
    è¿ĩåĪĨ
    0.21
    ä¸įæĦ¿æĦı
    0.21
    Activations Density 0.062%

    No Known Activations