© 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. 14436
    Prev
    Next
    INDEX
    Explanations

    Executor, Executrix, Trustee

    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
    çļĦä¸ľè¥¿
    -0.20
     discipline
    -0.20
    duct
    -0.20
    å¹ħ
    -0.19
    belongs
    -0.19
    slide
    -0.19
    -level
    -0.18
    edition
    -0.18
    ç¥ŀç§ĺ
    -0.18
    æı´
    -0.17
    POSITIVE LOGITS
    å±¥èģĮ
    0.19
    ATAB
    0.19
    æºī
    0.19
    èģĮæĿĥ
    0.19
    -sdk
    0.19
     substituted
    0.18
    æ¸ħçIJĨ
    0.18
    åĦ¡
    0.18
    usta
    0.18
     Rena
    0.18
    Activations Density 0.017%

    No Known Activations