© 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. 1767
    Prev
    Next
    INDEX
    Explanations

    All-American, All-Star, All-time

    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
    alone
    -0.08
    æİĮæŁľ
    -0.08
     fing
    -0.08
     Dare
    -0.08
    Ä°M
    -0.08
    æĶ¿
    -0.08
    (gui
    -0.08
    çķĮå®ļ
    -0.08
     Haus
    -0.08
    (EXPR
    -0.08
    POSITIVE LOGITS
    aghan
    0.10
     Unity
    0.09
    æ¼Ķ
    0.09
    unity
    0.09
    æ¸į
    0.09
    æ¶Ŀ
    0.09
    cep
    0.09
    æĽĻ
    0.09
    ourd
    0.09
    .addObserver
    0.09
    Activations Density 0.006%

    No Known Activations