© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8322
    Prev
    Next
    INDEX
    Explanations

    wheels and tires

    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
    æĢ¥
    -0.10
    åĩī
    -0.09
    FFE
    -0.09
    äºİæĺ¯
    -0.09
    åĭĴ
    -0.09
    éĻIJé¢Ŀ
    -0.08
    æĸ¼æĺ¯
    -0.08
     Salem
    -0.08
    èĢħçļĦ
    -0.08
     Maid
    -0.08
    POSITIVE LOGITS
    èĩ»
    0.10
    ess
    0.09
    ·»
    0.09
     пом
    0.08
    Eq
    0.08
    èݹ
    0.08
     crem
    0.08
    èŁ¾
    0.08
    Fred
    0.08
     ØŃÙĪ
    0.08
    Activations Density 0.085%

    No Known Activations