© 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. 16758
    Prev
    Next
    INDEX
    Explanations

    private sector

    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
    ãģĹãģı
    -0.20
    æ°ijæĹıæĸĩåĮĸ
    -0.18
    令人
    -0.18
    udos
    -0.17
     locals
    -0.17
    æľīæķĪæľŁ
    -0.17
     Incoming
    -0.17
    mits
    -0.17
    æŃ£éĿ¢
    -0.17
     mere
    -0.17
    POSITIVE LOGITS
    /private
    0.19
    -sector
    0.19
     sector
    0.19
    ä¼ģä¸ļåľ¨
    0.19
    /Form
    0.19
    apat
    0.19
     companies
    0.18
    åĬĽæ°Ķ
    0.18
    åĬĽéĩı
    0.18
    èIJ¥åĪ©
    0.18
    Activations Density 0.018%

    No Known Activations