© 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. 47957
    Prev
    Next
    INDEX
    Explanations

    dot videos, link, dailymotion, slashdot

    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
    çİij
    -0.11
    空
    -0.10
    çŃļ
    -0.08
    请èģĶç³»
    -0.08
    ä¸įå¿ĺ
    -0.08
    åįŀ
    -0.08
    仨
    -0.08
     bis
    -0.08
    裨
    -0.08
    piece
    -0.08
    POSITIVE LOGITS
    æĬķ票
    0.10
    绿
    0.09
    ÑĦон
    0.09
    çĤ¹äºĨ
    0.09
     Shib
    0.09
    preload
    0.09
    æĿĥéĩį
    0.09
    MAND
    0.09
    orrow
    0.09
    çĦĺ
    0.08
    Activations Density 0.019%

    No Known Activations