© 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. 35786
    Prev
    Next
    INDEX
    Explanations

    names of athletes and sports figures

    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
    æ·Ļ
    -0.09
    uda
    -0.09
    èŀĤ
    -0.09
    æĪĸå°Ĩ
    -0.09
    èµĥ
    -0.09
    ç¾İèģĶ
    -0.08
    è±¹
    -0.08
    éĢł
    -0.08
    åħļåĴĮæĶ¿åºľ
    -0.08
    atum
    -0.08
    POSITIVE LOGITS
    æĬij
    0.11
     Sterling
    0.10
    ç¿İ
    0.10
    çĬĢ
    0.10
    èĹ
    0.09
    _UNICODE
    0.09
    alion
    0.09
    rack
    0.08
    .instant
    0.08
     ÐĽÑİ
    0.08
    Activations Density 0.023%

    No Known Activations