© 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. 29986
    Prev
    Next
    INDEX
    Explanations

    archive and archival

    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
    çĶij
    -0.09
    çIJ®
    -0.09
     Trot
    -0.09
    é²·
    -0.09
    éķ¿æĺ¥
    -0.08
    лÑı
    -0.08
    åĽŀæĥ³
    -0.08
    URN
    -0.08
    å¿ı
    -0.08
    岸
    -0.08
    POSITIVE LOGITS
    yard
    0.11
    室
    0.10
     Bale
    0.10
    å·¥ä¸ļä¼ģä¸ļ
    0.10
    enic
    0.10
    yards
    0.09
    èĢĹ
    0.09
    çĶ¾
    0.09
    -Feb
    0.09
    åIJŀ
    0.09
    Activations Density 0.010%

    No Known Activations