© 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. 51512
    Prev
    Next
    INDEX
    Explanations

    United States courts

    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
    odore
    -0.11
    顾
    -0.09
    è¶ħ
    -0.09
    виÑĤ
    -0.09
    aina
    -0.09
    elib
    -0.09
    ayas
    -0.09
    许å¤ļ
    -0.08
    менно
    -0.08
    oves
    -0.08
    POSITIVE LOGITS
    ç½ijé¦ĸ页
    0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    0.09
    å¨ģåIJį
    0.09
     kob
    0.08
    å§Ķç»Ħç»ĩéĥ¨
    0.08
    æĺ¯éŁ©åĽ½
    0.08
    è¿Ļ份
    0.08
    è¿Ļ个è¡Įä¸ļ
    0.08
    éļĶéŁ³
    0.08
    ÙĴ
    0.08
    Activations Density 0.112%

    No Known Activations