© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9327
    Prev
    Next
    INDEX
    Explanations

    charged or tasked with

    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
    esto
    -0.10
    éªĦ
    -0.10
    èµĽåIJİ
    -0.09
    åĮºåĨħ
    -0.09
    inand
    -0.09
    æ¼Ķ
    -0.09
    ä¸įå®ļ
    -0.09
     Ä°lk
    -0.09
    åĿŀ
    -0.09
    oque
    -0.08
    POSITIVE LOGITS
    éĩįä»»
    0.10
    æĺ¥ç§ĭ
    0.09
    åīįè¿Ľ
    0.09
    èī°å·¨
    0.09
    åıµ
    0.09
    ç¼ĵæħ¢
    0.09
    饱满
    0.08
    orb
    0.08
    åľ¨è¿ĩ渡
    0.08
    ãģĦãģŁãģł
    0.08
    Activations Density 0.027%

    No Known Activations