© 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. 35392
    Prev
    Next
    INDEX
    Explanations

    without any warranties or damages

    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
    éĴ
    -0.09
    é¹Ĭ
    -0.09
    åĬ¡å·¥
    -0.08
    翻身
    -0.08
    åĶ¤
    -0.08
    æijĨæĶ¾
    -0.08
    ãĥ¼ãĤ·
    -0.08
    交ä¼ļ
    -0.08
     Needle
    -0.08
    è¯ģåĪ¸æĬķèµĦ
    -0.08
    POSITIVE LOGITS
    .hu
    0.09
    elian
    0.09
    elman
    0.08
    åºľ
    0.08
    èķ¾
    0.08
    عز
    0.08
    ircular
    0.08
    sembl
    0.08
    æľīæĦıæĢĿ
    0.08
    æ½Ń
    0.08
    Activations Density 0.030%

    No Known Activations