© 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. 4751
    Prev
    Next
    INDEX
    Explanations

    big [noun]

    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
    åİ¥
    -0.11
    ä¹Łè®©
    -0.09
    oha
    -0.09
    å°ij
    -0.09
    çľ¼æ³ª
    -0.08
    imary
    -0.08
    æĮ½
    -0.08
    æŀģå°ij
    -0.08
    ç¼Ń
    -0.08
    bir
    -0.08
    POSITIVE LOGITS
    çłĶ究表æĺİ
    0.09
    -grand
    0.09
    æ¤ħ
    0.09
    çıı
    0.09
    uan
    0.08
     ÙħÙĤابÙĦ
    0.08
    BuilderFactory
    0.08
    æĺ¥åŃ£
    0.08
    pte
    0.08
    çŁ¥æĥħ
    0.08
    Activations Density 0.018%

    No Known Activations