© 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. 15908
    Prev
    Next
    INDEX
    Explanations

    refineries, clubs, colonies, allergy

    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
    ä¸įèī¯ä¿¡æģ¯
    -0.19
    æıŃéľ²
    -0.19
    RefPtr
    -0.18
    å¿Ŀ
    -0.18
     Rowe
    -0.18
     !***
    -0.18
    ä»Ģä¹Īäºĭ
    -0.18
    åĢĴéľī
    -0.18
    alla
    -0.18
    ä¹Ĵä¹ĵ
    -0.18
    POSITIVE LOGITS
    ãħ¤
    0.18
    utes
    0.17
    ril
    0.17
    交æį¢
    0.17
    路线
    0.17
    ugar
    0.17
    æĢ»èĢĮè¨Ģä¹ĭ
    0.17
    å¼ģ
    0.17
    ä¸ŃåİŁ
    0.17
     vtx
    0.16
    Activations Density 1.059%

    No Known Activations