© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9822
    Prev
    Next
    INDEX
    Explanations

    special characters followed by words

    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
    éłĵ
    -0.10
    æľĢåĸľæ¬¢çļĦ
    -0.09
    çIJ¨
    -0.09
    çļĦéĤ£ä¸ª
    -0.09
    éĥ½çŁ¥éģĵ
    -0.09
    æĮ«
    -0.09
    åı£ä¸Ń
    -0.08
    æľīå¤ļå°ij
    -0.08
    äºĨå¤ļå°ij
    -0.08
    ael
    -0.08
    POSITIVE LOGITS
    oure
    0.09
    [](
    0.08
    REE
    0.08
    ichten
    0.08
    rok
    0.08
    abilia
    0.08
    eners
    0.08
    ution
    0.08
    tic
    0.08
    _bm
    0.08
    Activations Density 0.226%

    No Known Activations