© 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. 21168
    Prev
    Next
    INDEX
    Explanations

    university after from

    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
    åľ¨å¹¿å·ŀ
    -0.11
    强èĢħ
    -0.10
     пÑĢин
    -0.09
    åľ¨æ·±åľ³
    -0.09
    éĴ¢åİĤ
    -0.09
    èIJ¥è¿IJ
    -0.09
    abet
    -0.09
    éģĹ
    -0.08
    ieg
    -0.08
    èĬĤ缮
    -0.08
    POSITIVE LOGITS
    utar
    0.10
    大åѦæ¯ķä¸ļ
    0.09
     nearby
    0.09
    èĵĬ
    0.09
    饶
    0.08
    OK
    0.08
    vir
    0.08
    èķĻ
    0.08
    é¥
    0.08
    ç¥Ł
    0.08
    Activations Density 0.043%

    No Known Activations