© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50521
    Prev
    Next
    INDEX
    Explanations

    places ending with .com or hotel

    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
    寧
    -0.09
    enia
    -0.09
    acco
    -0.09
    era
    -0.08
    enic
    -0.08
    éĤ¬
    -0.08
    æĸĩåĮĸæĹħ游
    -0.08
     Onion
    -0.08
    èĦī
    -0.08
    å°ijçĪ·
    -0.08
    POSITIVE LOGITS
     Dzi
    0.09
    iba
    0.08
    è¿Ļåıª
    0.08
    å±Ģ
    0.08
    çĻ»ä¸Ĭ
    0.08
    mand
    0.08
    麻çĹ¹
    0.08
     Fighting
    0.08
    æĪİ
    0.08
     Jerome
    0.08
    Activations Density 0.015%

    No Known Activations