© 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. 9247
    Prev
    Next
    INDEX
    Explanations

    fees and data limits

    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
    æ°Ķæ°Ľ
    -0.10
    æĪİ
    -0.10
    åĿļå®ļä¸į移
    -0.09
    å¸Ĥåľºè§Ħ模
    -0.09
    nia
    -0.09
    åĨ³ä¸į
    -0.09
    strap
    -0.09
    .getElementsByName
    -0.09
    èĢ³è¾¹
    -0.09
    æĺ´
    -0.09
    POSITIVE LOGITS
     Usage
    0.11
     usage
    0.10
    usage
    0.10
    计
    0.10
    Usage
    0.10
    è¶ħåĩº
    0.10
    æ¯ıæľĪ
    0.10
    æľīä¸Ģ次
    0.09
    éĺ¶æ¢¯
    0.09
    æŃ£å¸¸ä½¿çĶ¨
    0.09
    Activations Density 0.059%

    No Known Activations