© 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. 13588
    Prev
    Next
    INDEX
    Explanations

    corporate tyranny

    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
     пÑĥ
    -0.23
    orias
    -0.21
     DISPATCH
    -0.21
    ä¼łåĩº
    -0.21
    InputElement
    -0.20
     DÅ©ng
    -0.19
     Ãĸnceki
    -0.19
     COMM
    -0.19
    ventus
    -0.19
    urrent
    -0.19
    POSITIVE LOGITS
    æݧåĪ¶åĻ¨
    0.22
     technology
    0.21
     controller
    0.20
    èģĶç½ij
    0.20
     Tang
    0.20
     manufacture
    0.20
     society
    0.20
     system
    0.20
    æľºåĻ¨äºº
    0.19
    åIJĦ家
    0.19
    Activations Density 0.053%

    No Known Activations