© 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. 55958
    Prev
    Next
    INDEX
    Explanations

    .h files and c drivers

    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
    æıĸ
    -0.10
    éĤĵå°ı
    -0.09
    æIJ½
    -0.09
    anyl
    -0.09
    æĵ¦æĭŃ
    -0.09
    åħļæĶ¿
    -0.08
    åĪ¸
    -0.08
    檫
    -0.08
    ona
    -0.08
    edx
    -0.08
    POSITIVE LOGITS
    太æ¹ĸ
    0.10
    ÅĦ
    0.09
    Going
    0.09
    baum
    0.09
     Wenger
    0.09
    ä¸ĭæīĭ
    0.09
    unset
    0.08
    ibern
    0.08
     Governors
    0.08
     Pistons
    0.08
    Activations Density 0.223%

    No Known Activations