© 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. 12087
    Prev
    Next
    INDEX
    Explanations

    power supply connections and lines

    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
    æ¼ł
    -0.22
    	iNdEx
    -0.20
     sod
    -0.20
    æĭīæĸ¯
    -0.19
    èĮ§
    -0.19
    ods
    -0.19
    ytt
    -0.19
     yards
    -0.19
    odos
    -0.19
    èĮħ
    -0.19
    POSITIVE LOGITS
    ä¾ĽåºĶ
    0.28
    ä¾ĽçĶµ
    0.26
     köln
    0.24
    çĶµæºIJ
    0.23
    upply
    0.23
    èĥ½æºIJ
    0.23
     supply
    0.22
    èµĦéĩij
    0.22
    supply
    0.22
     пиÑĤаниÑı
    0.22
    Activations Density 0.112%

    No Known Activations