© 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. 11982
    Prev
    Next
    INDEX
    Explanations

    organizational leadership roles

    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
    éĿ¢åŃĶ
    -0.21
    è´§
    -0.20
    çĽijæݧ
    -0.19
    岬
    -0.19
    mast
    -0.18
    åłµå¡ŀ
    -0.18
    ä¸ĢåĿĹ
    -0.18
     baggage
    -0.18
    ä¿®çIJĨ
    -0.17
    å¾Ĺä½ı
    -0.17
    POSITIVE LOGITS
    å§Ķ
    0.27
    ÑĦин
    0.23
    æľīéĻIJ
    0.20
    жÑĥ
    0.19
    Contracts
    0.19
    pha
    0.19
    pio
    0.18
    ä¹ĸ
    0.18
    bout
    0.18
     Pyramid
    0.18
    Activations Density 0.025%

    No Known Activations