© 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. 16120
    Prev
    Next
    INDEX
    Explanations

    artificial or synthetic constructs

    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
    returnValue
    -0.18
     Bare
    -0.18
    人身
    -0.17
    opot
    -0.17
    REW
    -0.17
    otre
    -0.17
    -follow
    -0.17
    oire
    -0.17
    ToPoint
    -0.17
    æīĢå±ŀ
    -0.17
    POSITIVE LOGITS
    -made
    0.23
    -born
    0.22
    天河
    0.21
     created
    0.20
     synthetic
    0.20
     reality
    0.20
    æĢ§å¼º
    0.20
    	Created
    0.19
    èĢĮæĪIJ
    0.19
    -generated
    0.18
    Activations Density 0.080%

    No Known Activations