© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8685
    Prev
    Next
    INDEX
    Explanations

    -esque suffixes

    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
    èĨº
    -0.09
    æº
    -0.09
    踽
    -0.09
    说çļĦè¯Ŀ
    -0.09
    ä¹ĥæĺ¯
    -0.09
    ãĤ³ãĥ¼ãĥ
    -0.08
    æĦģ
    -0.08
    illion
    -0.08
    éĥľ
    -0.08
    ugg
    -0.08
    POSITIVE LOGITS
    ä¸ĭæīĭ
    0.09
    -esque
    0.09
    ixo
    0.09
    .mdl
    0.08
     barg
    0.08
    缩å°ı
    0.08
    è¡Ģèħ¥
    0.08
    æļ´åĬĽ
    0.08
    ertools
    0.08
    è´«è¡Ģ
    0.08
    Activations Density 0.006%

    No Known Activations