© 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. 52753
    Prev
    Next
    INDEX
    Explanations

    career ending injury retirement injury comeback

    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
    ä¸ŃåĽ½åĪ¶éĢł
    -0.11
     Escort
    -0.10
    arks
    -0.10
    糧
    -0.10
    ç²®
    -0.09
    åľ°çIJĥä¸Ĭ
    -0.09
     ÐłÐ°Ñģ
    -0.09
    orent
    -0.09
    æĭ¥æĮ¤
    -0.09
    ucus
    -0.09
    POSITIVE LOGITS
    éĢĢå½¹
    0.16
    伤
    0.12
     Injury
    0.12
    伤çĹħ
    0.12
     injury
    0.12
     injuries
    0.11
    è¿IJåĬ¨åijĺ
    0.11
    èĨĿçĽĸ
    0.10
    åıĹ伤
    0.10
    æľįå½¹
    0.10
    Activations Density 0.265%

    No Known Activations