© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 17145
    Prev
    Next
    INDEX
    Explanations

    social connections and networks

    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
    Negative Logits
    èĬŁ
    -0.20
    ãģĦãģĨ
    -0.19
    åıĮåıĮ
    -0.19
    reducers
    -0.19
    人ãģ«
    -0.18
    èķ´
    -0.18
    æĬľ
    -0.18
    ä¿ĦåĨĽ
    -0.18
    าว
    -0.18
     Wilson
    -0.17
    POSITIVE LOGITS
     contacts
    0.29
    contacts
    0.28
     dealings
    0.24
    人èĦī
    0.23
    åľĪ
    0.22
     networks
    0.22
     ties
    0.22
     khắp
    0.22
    åĽ½åĨħå¤ĸ
    0.21
    æľĭåıĭåľĪ
    0.21
    Activations Density 0.033%

    No Known Activations