© 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. 62471
    Prev
    Next
    INDEX
    Explanations

    recruitment and trial

    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
    åĽ½åĬ¡
    -0.09
     Pause
    -0.09
     пÑĥ
    -0.09
     ÑģÑĦ
    -0.09
    Pause
    -0.09
    éĤ£ä»½
    -0.08
    éĺı
    -0.08
    æĮĩçĤ¹
    -0.08
    æĪ¿ä¸ľ
    -0.08
    edList
    -0.08
    POSITIVE LOGITS
    æĭĽåĭŁ
    0.21
     recruitment
    0.20
    éĢīæĭĶ
    0.18
     recruiting
    0.18
    æĭĽçĶŁ
    0.18
    æĭĽèģĺ
    0.18
     recruit
    0.17
     Recruitment
    0.17
    éĿ¢è¯ķ
    0.16
    æĭĽ
    0.16
    Activations Density 0.256%

    No Known Activations