© 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. 37028
    Prev
    Next
    INDEX
    Explanations

    politicians' last names

    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
     оÑĤкÑĢÑĭÑĤ
    -0.09
    çªĪ
    -0.09
    å¼ĢæĶ¾å¼ı
    -0.09
    ottle
    -0.09
    åĪ©äºļ
    -0.08
     initials
    -0.08
    ç¼ħ
    -0.08
    âĤ¬âĦ¢
    -0.08
     fat
    -0.08
    åħī线
    -0.08
    POSITIVE LOGITS
    ä¸Ģ次æĢ§
    0.09
    èīº
    0.09
     INCLUDE
    0.09
    parsers
    0.08
    åľ¨æĹ¥æľ¬
    0.08
    ajor
    0.08
    ç»ıæµİæĬĢæľ¯
    0.08
    å®īæİĴ
    0.08
     Tort
    0.07
    rush
    0.07
    Activations Density 0.016%

    No Known Activations