© 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. 3727
    Prev
    Next
    INDEX
    Explanations

    Battlefield 1 team

    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
    åıĺå¼Ĥ
    -0.09
    æ£Ĵ
    -0.09
    PIO
    -0.09
    åĨįéĢł
    -0.09
    ewise
    -0.09
    æŃ¦ä¾ł
    -0.09
    ä¸ĸçķĮè§Ĥ
    -0.09
    åıĤä¸İèĢħ
    -0.08
    ä¸įäºĨ解
    -0.08
    æłİ
    -0.08
    POSITIVE LOGITS
     Bott
    0.08
    æ±Łæ·®
    0.08
     kok
    0.08
    å¿ĥå¢ĥ
    0.08
     soul
    0.08
    udder
    0.08
    åī²
    0.08
    æĢ§æł¼
    0.08
    åįij
    0.08
     unlink
    0.08
    Activations Density 0.039%

    No Known Activations