© 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. 37117
    Prev
    Next
    INDEX
    Explanations

    semifinals

    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
    æĢ»çļĦ
    -0.10
    ä¸ĥæĺŁ
    -0.09
     Maul
    -0.09
    åİķ
    -0.09
    å¿¿
    -0.09
    eil
    -0.09
    INY
    -0.09
    è¿Ļ个åIJįåŃĹ
    -0.09
    ãĥIJãĥĥãĤ¯
    -0.08
    onal
    -0.08
    POSITIVE LOGITS
    ä¹ĥèĩ³
    0.10
    çĶļèĩ³
    0.09
    lesen
    0.09
    寮
    0.09
    town
    0.08
    éģĺ
    0.08
    eyer
    0.08
    etros
    0.08
    cdr
    0.08
    çľ¼ä¸ĭ
    0.08
    Activations Density 0.007%

    No Known Activations