© 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. 15242
    Prev
    Next
    INDEX
    Explanations

    books and course materials

    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
    éĺį
    -0.23
    å¡Į
    -0.19
     ju
    -0.19
    å§ĺ
    -0.19
     pensions
    -0.18
    å¨ĵ
    -0.18
     signs
    -0.18
    è°¥
    -0.18
     value
    -0.18
    é«ĺæīĭ
    -0.18
    POSITIVE LOGITS
    å¿ħè¦ģçļĦ
    0.28
    æ¹Ľ
    0.26
    å¼ĢåѦ
    0.26
    æĸ°æĿIJæĸĻ
    0.24
    ä¸Ĭ课
    0.23
    å¿ħéľĢ
    0.23
    åħ¥åѦ
    0.23
     isbn
    0.23
    å¿ħä¸įåı¯å°ij
    0.22
    Required
    0.22
    Activations Density 0.011%

    No Known Activations