© 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. 37296
    Prev
    Next
    INDEX
    Explanations

    drive-thru restaurantDrive, NightcrawlerMarine DriveColumbus DriveDodson DriveMorning DriveProsperity Lake DriveWashmill Lake DriveBelle Pond Drive

    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
    æ³Ľ
    -0.10
    é¦Ĩ
    -0.10
    nga
    -0.09
    å¥Ĥ
    -0.09
    é¦ĸåıij
    -0.09
    éĽĨåĽ¢èĤ¡ä»½
    -0.09
    箨
    -0.09
     Ferry
    -0.08
    ä¸ŃåĽ½ç§»åĬ¨
    -0.08
    ãģĦãĤĭ
    -0.08
    POSITIVE LOGITS
    çĦĻ
    0.09
     textbook
    0.09
     Lomb
    0.09
    å°ļ
    0.09
     rer
    0.09
    åŃĿ
    0.08
    è¯¾æľ¬
    0.08
    EMA
    0.08
    iful
    0.08
    å¼ı
    0.08
    Activations Density 0.007%

    No Known Activations