© 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. 38991
    Prev
    Next
    INDEX
    Explanations

    elite groups and institutions

    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
    åıĭè°Ĭ
    -0.10
    èĢĥå¯Ł
    -0.08
    éŨå¤ĸ
    -0.08
    人类
    -0.08
     friendship
    -0.08
    ä¸ĸçķĮä¸Ĭ
    -0.08
     ìļ°ë¦¬ëĤĺëĿ¼
    -0.08
    ä¸ĸçķĮåIJĦåĽ½
    -0.08
    åľ¨æĪijåĽ½
    -0.08
    å½ĵä»Ĭ
    -0.07
    POSITIVE LOGITS
    çĽ¸å¯¹è¾ĥ
    0.11
    横åIJij
    0.10
    åĬ¨åijĺ
    0.09
    主ä½ĵ
    0.09
    为主ä½ĵ
    0.09
    åħ§éĥ¨
    0.09
    층
    0.09
    纵åIJij
    0.09
    åħ¬åħ±æľįåĬ¡
    0.09
    çĽ¸å¯¹æĿ¥è¯´
    0.09
    Activations Density 0.096%

    No Known Activations