© 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. 37827
    Prev
    Next
    INDEX
    Explanations

    finding jobs and employment

    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
    èĮĨ
    -0.10
    Cond
    -0.09
    æĨĶ
    -0.09
    绵
    -0.09
     Cond
    -0.09
    ondon
    -0.09
    ä¸ĭè¾¾
    -0.09
    .mobile
    -0.09
    izu
    -0.09
    åĩĿ
    -0.09
    POSITIVE LOGITS
    å°±ä¸ļ
    0.21
    å°±ä¸ļå²Ĺä½į
    0.21
     jobs
    0.17
    å·¥ä½ľå²Ĺä½į
    0.17
     employment
    0.16
    jobs
    0.15
    å²Ĺä½į
    0.15
     job
    0.15
    èģĮä½į
    0.14
    employment
    0.14
    Activations Density 0.168%

    No Known Activations