© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37076
    Prev
    Next
    INDEX
    Explanations

    hiring or outsourcing

    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
    éĺĶ
    -0.09
    isl
    -0.09
    ç¢į
    -0.09
    对她
    -0.08
     poster
    -0.08
    æ¡Ģ
    -0.08
    ç¤Ļ
    -0.08
     posters
    -0.08
    举è¡Į
    -0.08
    aint
    -0.08
    POSITIVE LOGITS
    å¤ĸåĮħ
    0.16
    ä»ĸ人
    0.15
    å§Ķæīĺ
    0.14
     outsourcing
    0.13
    hire
    0.13
    èģĺçĶ¨
    0.13
    åĪ¥äºº
    0.13
    åĪ«äººçļĦ
    0.13
     hire
    0.13
    éĽĩ
    0.13
    Activations Density 0.173%

    No Known Activations