© 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. 39674
    Prev
    Next
    INDEX
    Explanations

    company names and entities

    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
     Bosch
    -0.08
    ä¼Łå¤§
    -0.08
    è´´
    -0.08
    ä¸Ļ
    -0.08
    èĥ¡
    -0.08
    éºŁ
    -0.08
    angen
    -0.08
    ersen
    -0.08
    讨
    -0.08
     traction
    -0.08
    POSITIVE LOGITS
    éĽĨåĽ¢èĤ¡ä»½
    0.13
    æݧèĤ¡èĤ¡ä¸ľ
    0.11
    ä¸Ģåı£
    0.09
    æijĨæĶ¾
    0.09
    æĬ«éľ²
    0.09
    åģ»
    0.09
    uddle
    0.09
    åĤ¥
    0.09
    åģľçīĮ
    0.09
    spi
    0.09
    Activations Density 0.059%

    No Known Activations