© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 52260
    Prev
    Next
    INDEX
    Explanations

    physical sensation and action

    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
    ä¸īæľŁ
    -0.09
    åĪ·
    -0.09
     Briggs
    -0.09
    çľ¼åīįçļĦ
    -0.08
    çľĭåIJij
    -0.08
    è¾IJ
    -0.08
    iley
    -0.08
    æŃ¥è¡Į
    -0.08
    çݰ身
    -0.08
    çħħ
    -0.08
    POSITIVE LOGITS
    å¾Īå¼Ģå¿ĥ
    0.10
    麻
    0.10
    鼶è·Ŀ离
    0.09
    幸ç¦ıæĦŁ
    0.09
    æĬļæij¸
    0.09
    äºĴåĬ¨
    0.09
    ç͍åĬĽ
    0.09
    ENG
    0.09
     Gors
    0.09
    çĹĴ
    0.09
    Activations Density 0.034%

    No Known Activations