© 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. 33154
    Prev
    Next
    INDEX
    Explanations

    take you through

    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
    uges
    -0.09
    é¢ĩ
    -0.09
    ä¿Ł
    -0.08
    èĽĨ
    -0.08
    ä¹Łéļıä¹ĭ
    -0.08
    auc
    -0.08
    æİ¨è¿Ł
    -0.08
    .truth
    -0.08
    IRON
    -0.08
    延éķ¿
    -0.08
    POSITIVE LOGITS
    åħ»çĮª
    0.10
    å¼ĢäºĨ
    0.10
    ogle
    0.09
     anc
    0.09
    ظÙĦÙħ
    0.08
    é¢Ĩçķ¥
    0.08
     Dund
    0.08
     Oz
    0.08
    æľīéĻIJ
    0.08
    \Db
    0.08
    Activations Density 0.030%

    No Known Activations