© 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. 36768
    Prev
    Next
    INDEX
    Explanations

    institutions or organizations

    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
    æķ´ä¸ª
    -0.11
    avier
    -0.09
    åıĻ
    -0.09
    eren
    -0.09
    æ´¾åĩºæīĢ
    -0.09
     оÑģÑĤа
    -0.09
    zie
    -0.08
    èģ¿
    -0.08
    newInstance
    -0.08
    ORS
    -0.08
    POSITIVE LOGITS
    天é¹ħ
    0.10
    çļĦå¿ĥçIJĨ
    0.08
     Sandra
    0.08
    -inner
    0.08
    å®ĺ
    0.08
    æĺ¯éŁ©åĽ½
    0.08
    ä¸Ńåľº
    0.08
    æ¯ıå¹´éĥ½
    0.07
    èĬ®
    0.07
    çļĦ家åºŃ
    0.07
    Activations Density 0.179%

    No Known Activations