© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51003
    Prev
    Next
    INDEX
    Explanations

    attends, participates, work, woman

    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
    åħ·æľīèī¯å¥½
    -0.08
     Twilight
    -0.08
    eed
    -0.08
    çīį
    -0.08
    dle
    -0.08
    ÙĴ
    -0.08
    cts
    -0.08
    LOT
    -0.08
    owel
    -0.08
    绿水
    -0.08
    POSITIVE LOGITS
    åĽ¾ä¸º
    0.15
    åĽ¾çīĩæĿ¥æºIJ
    0.13
    çļĦçħ§çīĩ
    0.13
    ä¾ĽåĽ¾
    0.12
     photo
    0.11
    åĽ¾çīĩ
    0.11
    çħ§çīĩ
    0.11
    示æĦı
    0.11
    åľĸçīĩ
    0.10
    çī¹åĪ«æĺ¯åľ¨
    0.10
    Activations Density 0.380%

    No Known Activations