© 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. 49528
    Prev
    Next
    INDEX
    Explanations

    exclamations or questions

    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
    éĦĻ
    -0.10
    puter
    -0.10
    åħ³éĶ®æĬĢæľ¯
    -0.09
    æĤ²åĵĢ
    -0.09
    ä¸Ģ件äºĭ
    -0.09
     crossword
    -0.08
    çĬ¯ç½ªå«Įçĸij
    -0.08
    欢è¿İæĤ¨
    -0.08
    ãĤ¤ãĥ«
    -0.08
    è°¨
    -0.08
    POSITIVE LOGITS
    ä¸ºçĽ®çļĦ
    0.10
    ä¸ºçĽ®æłĩ
    0.09
     Tar
    0.08
    çĬĬ
    0.08
    æĬĬè¿ĻäºĽ
    0.08
    _ORIGIN
    0.08
     Og
    0.08
    å¼ĵ
    0.08
    彤
    0.08
    cury
    0.08
    Activations Density 0.063%

    No Known Activations