© 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. 11829
    Prev
    Next
    INDEX
    Explanations

    friends and friendship

    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
    inium
    -0.20
    ä¸Ģç«Ļ
    -0.20
    èĭ
    -0.19
    æĿijæ°ij们
    -0.19
    -Mart
    -0.19
    æĥħä¾£
    -0.19
    istem
    -0.18
    пи
    -0.18
    aders
    -0.18
    ä¹ĸä¹ĸ
    -0.18
    POSITIVE LOGITS
    好åıĭ
    0.44
    åıĭæĥħ
    0.35
    åıĭ
    0.35
    æľĭåıĭ
    0.34
    åıĭ好
    0.33
    	friend
    0.32
    çļĦæľĭåıĭ
    0.32
     friendship
    0.32
     friend
    0.32
     friends
    0.30
    Activations Density 0.107%

    No Known Activations