© 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. 7218
    Prev
    Next
    INDEX
    Explanations

    Rashford, employees, case, have

    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
    åªĴ
    -0.10
    éĺķ
    -0.09
    èķī
    -0.09
    ä¸Ģ个æĸ°çļĦ
    -0.08
    å³°åĢ¼
    -0.08
    éķĿ
    -0.08
    åıĸèĥľ
    -0.08
    çķ
    -0.08
    çīĩ
    -0.08
     Oc
    -0.08
    POSITIVE LOGITS
    .getAs
    0.09
     Sle
    0.09
    æ¼Ĥ
    0.09
    åIJĦæĸ¹éĿ¢
    0.08
    tk
    0.08
     Evangel
    0.08
    梦幻
    0.08
    éĢĢå¸Ĥ
    0.08
    éĢł
    0.08
    OTES
    0.08
    Activations Density 0.004%

    No Known Activations