© 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. 49046
    Prev
    Next
    INDEX
    Explanations

    job interviews

    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
    arov
    -0.11
    æĭ¥æĮ¤
    -0.10
    æĽĻ
    -0.09
    åīĸ
    -0.09
    æīĺ
    -0.09
    åĪ¹
    -0.09
    æĶ»åĩ»
    -0.09
    顺åĬ¿
    -0.09
    转移
    -0.09
    æĶ¾åģĩ
    -0.09
    POSITIVE LOGITS
    éĿ¢è¯ķ
    0.17
    ç¬Ķè¯ķ
    0.11
    å½ķçĶ¨
    0.11
    å¤įè¯ķ
    0.11
     interview
    0.10
    åĢĻéĢī人
    0.10
    çĶ³è¯·äºº
    0.10
    çŃĽéĢī
    0.10
    åīįä¸Ģ天
    0.10
    å¿ĥ仪
    0.09
    Activations Density 0.230%

    No Known Activations