© 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. 55169
    Prev
    Next
    INDEX
    Explanations

    career advancement and promotions

    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
    éĹªçĶµ
    -0.08
    åķ®
    -0.08
    çī§
    -0.08
    åŀ¦
    -0.08
    èĢķ
    -0.08
    etes
    -0.08
    elier
    -0.08
    uest
    -0.08
    éĿĸ
    -0.08
    å¾ģæľį
    -0.08
    POSITIVE LOGITS
    æĻĭåįĩ
    0.23
    æıIJæĭĶ
    0.21
    åįĩ
    0.17
    æĵ¢
    0.16
     promotions
    0.14
    éĻŀ
    0.14
     promotion
    0.14
    ä»ķ
    0.13
    èģĮä¸ļçĶŁæ¶¯
    0.13
    æĻĭ级
    0.13
    Activations Density 0.074%

    No Known Activations