© 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. 1443
    Prev
    Next
    INDEX
    Explanations

    career or professions

    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
    ç»
    -0.08
    交æİ¥
    -0.08
    ç²¾åĵģ
    -0.08
    家ä½ı
    -0.08
    strup
    -0.08
     tán
    -0.08
    沩
    -0.08
    å°
    -0.08
    èĩ³ä¸Ĭ
    -0.08
    æ¯ıåij¨
    -0.08
    POSITIVE LOGITS
     careers
    0.13
    èģĮä¸ļ
    0.12
    career
    0.12
    èģĮä¸ļçĶŁæ¶¯
    0.12
     career
    0.11
     professions
    0.11
     Career
    0.10
    çĶŁæ¶¯
    0.10
    æ¼Ĥ
    0.10
    享
    0.10
    Activations Density 0.083%

    No Known Activations