© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 1765
    Prev
    Next
    INDEX
    Explanations

    relationship and social connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    寿
    -0.26
    éĢļè¡Į
    -0.25
     retiring
    -0.24
    人寿
    -0.24
    èĤ¡ä¸ľå¤§ä¼ļ
    -0.23
     contemporary
    -0.23
     fiscal
    -0.23
    akens
    -0.23
     loadChildren
    -0.23
     hall
    -0.22
    POSITIVE LOGITS
    æĥħä¾£
    0.34
    çĶ¨å¾®ä¿¡
    0.32
    çļĦæĦŁæĥħ
    0.27
     girlfriends
    0.27
     facebook
    0.27
    /twitter
    0.27
    æģĭæĥħ
    0.26
    çĶ·æľĭåıĭ
    0.26
    /social
    0.26
     boyfriend
    0.25
    Activations Density 0.018%

    No Known Activations