© 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. 50755
    Prev
    Next
    INDEX
    Explanations

    time of day or event

    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
    继ç»Ń
    -0.12
    æľ«ç«¯
    -0.10
    ç¹¼çºĮ
    -0.10
     пÑĢодолж
    -0.09
    æĸ°çĶŁ
    -0.09
    身åIJİ
    -0.09
     continue
    -0.09
     continues
    -0.09
    西路
    -0.08
     continued
    -0.08
    POSITIVE LOGITS
    åīįå¤ķ
    0.16
    å½ĵ天
    0.16
    å±ĬæŶ
    0.14
    éĤ£å¤©
    0.14
    åĪ°æŶåĢĻ
    0.13
    éĤ£ä¸Ģ天
    0.12
    å½ĵæĻļ
    0.12
    åīįä¸Ģ天
    0.12
    è¿Ļä¸Ģ天
    0.12
    å½ĵæĹ¥
    0.11
    Activations Density 0.092%

    No Known Activations