© 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. 14852
    Prev
    Next
    INDEX
    Explanations

    groups or communities

    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
    ä¸ŃåĽ½æĸĩåĮĸ
    -0.20
    mare
    -0.19
    综èīº
    -0.19
    å©Ĩ
    -0.19
    é«ĵ
    -0.19
    讣
    -0.19
    oeff
    -0.18
    éĩįå¿ĥ
    -0.18
    æIJ¬å®¶
    -0.18
    äºĮåŃĹ
    -0.18
    POSITIVE LOGITS
    åIJĮè¡Į
    0.43
     fellow
    0.41
     peers
    0.40
     others
    0.37
    åIJĮäºĭ
    0.36
    åIJĮä¼´
    0.36
    åħ¶ä»ĸ人
    0.35
    åħ¶ä»ĸ
    0.32
    åĪ«äºº
    0.31
    åIJĮæľŁ
    0.30
    Activations Density 0.170%

    No Known Activations