© 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. 61156
    Prev
    Next
    INDEX
    Explanations

    career and future plans

    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
    对ä»ĺ
    -0.09
    æ°ijå¿ĥ
    -0.09
    人èĦ¸
    -0.09
    èħ´
    -0.09
    çļĦåį°è±¡
    -0.09
    æŃ£å¸¸ä½¿çĶ¨
    -0.09
    æĤ²åĵĢ
    -0.09
    æīĭä¸ĭ
    -0.08
    å¸ĪçĶŁ
    -0.08
    对çĿĢ
    -0.08
    POSITIVE LOGITS
     career
    0.16
    èģĮä¸ļçĶŁæ¶¯
    0.15
    çļĦèģĮä¸ļ
    0.13
    èģĮä¸ļ
    0.13
     Career
    0.12
    çļĦ人çĶŁ
    0.12
    career
    0.12
    å°±ä¸ļ
    0.12
    Career
    0.12
    çĶŁæ¶¯
    0.11
    Activations Density 0.130%

    No Known Activations