© 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. 21306
    Prev
    Next
    INDEX
    Explanations

    years and dates

    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
    felt
    -0.09
    oins
    -0.09
    ennen
    -0.09
    oyal
    -0.09
    IDD
    -0.09
    bies
    -0.09
     вал
    -0.09
    OrCreate
    -0.09
    .variant
    -0.08
    èĥ¡åŃIJ
    -0.08
    POSITIVE LOGITS
    ä¸Ģçŀ¬éĹ´
    0.09
    å¹´çļĦ
    0.08
     Pil
    0.08
    кÑģ
    0.08
    ä¼ī
    0.08
    以ä¾Ĩ
    0.08
    æľŁ
    0.08
    ebin
    0.08
    기를
    0.08
    çŀ©
    0.08
    Activations Density 0.186%

    No Known Activations