© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21680
    Prev
    Next
    INDEX
    Explanations

    clique, promos, popularity, school

    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
    зи
    -0.09
     Lobby
    -0.09
    çľĭä½ł
    -0.09
    åŃIJåŃĻ
    -0.09
    åѦåijĺ
    -0.09
    家ä¸Ń
    -0.09
    å¼ĢåĬŀ
    -0.09
    çħ®
    -0.09
    æĮ£
    -0.09
    çĪ±æĬ¤
    -0.09
    POSITIVE LOGITS
    社交
    0.10
    æł¡
    0.09
    Cli
    0.09
    èģļä¼ļ
    0.09
     clique
    0.09
    é«ĺä¸ŃçĶŁ
    0.08
    æł¡åĽŃ
    0.08
    åIJĮåѦ
    0.08
    atus
    0.08
     cli
    0.08
    Activations Density 0.156%

    No Known Activations