© 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. 32703
    Prev
    Next
    INDEX
    Explanations

    general population

    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
    çĥŃ带
    -0.09
    imi
    -0.09
    é¼ĵåĬ±
    -0.09
    代åĬŀ
    -0.09
    åĬ¿
    -0.09
    åĬŀ
    -0.09
    æ©ĺ
    -0.09
    å¿łè¯ļ
    -0.08
    æĸ°æĶ¿
    -0.08
    ä»Ĩ
    -0.08
    POSITIVE LOGITS
    åħ¬ä¼Ĺ
    0.14
    大ä¼Ĺ
    0.14
    æ°ijä¼Ĺ
    0.11
    зна
    0.10
    ä¸ĸ人
    0.10
    ç§ijæĬĢèĤ¡ä»½
    0.09
    çĶļ
    0.09
    人群
    0.09
     Alger
    0.09
    鼶è·Ŀ离
    0.09
    Activations Density 0.185%

    No Known Activations