© 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. 13000
    Prev
    Next
    INDEX
    Explanations

    launching side network arm customers

    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
    å¥ı
    -0.21
    æį¢æĪIJ
    -0.20
    åıĹçĽĬ
    -0.20
    çł´
    -0.20
    æĭ±
    -0.20
    éĻ¬
    -0.20
    æĩĴ
    -0.19
    æºľ
    -0.18
    èĮļ
    -0.18
    èĢĥéĩı
    -0.18
    POSITIVE LOGITS
    èĩªæľī
    0.26
    èĩªä¸»çłĶåıij
    0.24
    æľīèĩªå·±çļĦ
    0.22
    æīĢæıIJä¾Ľ
    0.21
    产åĵģçłĶåıij
    0.19
    æĻºéĢł
    0.19
    capability
    0.19
    åĩºéģĵ
    0.19
    cult
    0.19
     Rhodes
    0.19
    Activations Density 0.271%

    No Known Activations