© 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. 12634
    Prev
    Next
    INDEX
    Explanations

    space missions and projects

    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
    æĴŃæĬ¥
    -0.23
    èIJ¥åķĨ
    -0.23
    xDF
    -0.23
    xBD
    -0.22
    éĢıè§Ĩ
    -0.21
    åķĨæĪ·
    -0.21
    åIJĦè¡ĮåIJĦ
    -0.21
    afone
    -0.20
    å·´èIJ¨
    -0.20
    çĸµ
    -0.20
    POSITIVE LOGITS
    æľªæĿ¥çļĦ
    0.27
    计åĪĴ
    0.26
     plan
    0.25
     missions
    0.25
     projects
    0.24
    大åŀĭ
    0.23
     plans
    0.23
    æĹ©æĹ¥
    0.23
    ä¸ĭä¸Ģ代
    0.23
    æĸ¹æ¡Ī
    0.23
    Activations Density 0.018%

    No Known Activations