© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51790
    Prev
    Next
    INDEX
    Explanations

    star rating

    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
    å¼
    -0.11
    ÌĢ
    -0.10
    åıijå±ķ模å¼ı
    -0.10
    ä¸ĸçķĮ第ä¸Ģ
    -0.09
    çIJ¢ç£¨
    -0.09
    ussion
    -0.09
    åħ¬äº¤è½¦
    -0.09
    åıijå±ķ空éĹ´
    -0.09
    çļĦè¯Ŀé¢ĺ
    -0.09
    èĥ½åĬĽå¼º
    -0.09
    POSITIVE LOGITS
    ä¸Ģ头
    0.10
    å°±åľ¨
    0.09
    é¡¶
    0.08
    led
    0.08
    corp
    0.08
    æłī
    0.08
    çĥģ
    0.08
    åĵįåºĶ
    0.08
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.08
    åħ¸åŀĭçļĦ
    0.08
    Activations Density 0.002%

    No Known Activations