© 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. 19223
    Prev
    Next
    INDEX
    Explanations

    social consequences, norms, change, history, networks, problem, work, Justice, media

    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
    eries
    -0.10
    tings
    -0.09
    erland
    -0.09
    人工
    -0.09
    人æ°Ķ
    -0.09
    ÑĪка
    -0.08
    irst
    -0.08
    oretical
    -0.08
    оÑģÑĮ
    -0.08
    ä¸ĸçķĮä¸ĬæľĢ
    -0.08
    POSITIVE LOGITS
    å·¥ä½ľèĢħ
    0.12
    -minded
    0.12
    ware
    0.12
    verständlich
    0.11
    åħ¬çĽĬ
    0.10
     loaf
    0.09
    ingles
    0.09
    åıĺè¿ģ
    0.09
    amedi
    0.09
    åĺ´åĶĩ
    0.09
    Activations Density 0.023%

    No Known Activations