© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19291
    Prev
    Next
    INDEX
    Explanations

    social and its related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
     circum
    -0.09
    ev
    -0.09
     wax
    -0.09
    èĬĹ
    -0.09
    åĭģ
    -0.09
    åĬĥ
    -0.09
    æ½ĩ
    -0.09
    çīĪæĿĥå½Ĵ
    -0.08
    aku
    -0.08
    èĥ¸éĥ¨
    -0.08
    POSITIVE LOGITS
    社交
    0.16
    交éĻħ
    0.14
    交å¾Ģ
    0.13
     social
    0.11
     Social
    0.10
    social
    0.10
    Interaction
    0.10
    åIJĮç±»
    0.10
    -social
    0.10
    çļĦ社ä¼ļ
    0.10
    Activations Density 0.084%

    No Known Activations