© 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. 9835
    Prev
    Next
    INDEX
    Explanations

    first person verbs and adverbs

    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
    ä½ľåĩºäºĨ
    -0.13
    çľĭäºĨä¸Ģ
    -0.12
    ç»ĻäºĨ
    -0.11
    åıĤåĬłäºĨ
    -0.11
    åģļåĩºäºĨ
    -0.11
    èİ·å¾ĹäºĨ
    -0.11
    ä½ľäºĨ
    -0.11
    ç»ĻäºĪäºĨ
    -0.10
    å½ĵæŶçļĦ
    -0.10
    çķĻä¸ĭäºĨ
    -0.10
    POSITIVE LOGITS
    ç»ı常
    0.13
    常çĶ¨
    0.13
    使çĶ¨
    0.12
    å®ļæľŁ
    0.12
    æ¯ıåij¨
    0.11
    æ¯ıå¹´
    0.11
    åĢ¾åIJijäºİ
    0.11
    æĹ¶å¸¸
    0.11
     иÑģполÑĮзÑĥÑİÑĤ
    0.11
     иÑģполÑĮзоваÑĤÑĮ
    0.11
    Activations Density 0.123%

    No Known Activations