© 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. 11937
    Prev
    Next
    INDEX
    Explanations

    Labor relations and contracts

    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
    qing
    -0.20
    åIJĮä¼´
    -0.18
    ä»ĸ人
    -0.18
    ä¸ļ主
    -0.18
    åĻİ
    -0.18
    ç¨İ
    -0.17
     Reign
    -0.17
    -fly
    -0.17
    i
    -0.17
     tit
    -0.17
    POSITIVE LOGITS
     Wak
    0.21
    ä¸ºæľŁ
    0.21
    olas
    0.20
    çĸ²
    0.19
    è¿ĽéŨ
    0.19
    笥
    0.19
    ckett
    0.19
    éĵ©
    0.19
    æľīæľŁ
    0.19
    äºĭå®ľ
    0.19
    Activations Density 0.011%

    No Known Activations